diff --git a/lectures/00_configuration/installcommands.txt b/lectures/00_configuration/installcommands.txt
index 48ba3dc..0e15e91 100644
--- a/lectures/00_configuration/installcommands.txt
+++ b/lectures/00_configuration/installcommands.txt
@@ -1,4 +1,5 @@
 pip install ipywidgets
 pip install scikit-learn
 pip install ultralytics 
-pip install ultralytics opencv-python
\ No newline at end of file
+pip install ultralytics opencv-python
+pip install transformers
\ No newline at end of file
diff --git a/lectures/03_linear_regressioin_autogradient/0_pytorch_fundamentals_A.ipynb b/lectures/03_linear_regressioin_autogradient/0_pytorch_fundamentals_A.ipynb
index 340a7f2..bf93a70 100644
--- a/lectures/03_linear_regressioin_autogradient/0_pytorch_fundamentals_A.ipynb
+++ b/lectures/03_linear_regressioin_autogradient/0_pytorch_fundamentals_A.ipynb
@@ -13,7 +13,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 1,
    "id": "739c5173",
    "metadata": {},
    "outputs": [
@@ -23,7 +23,7 @@
        "'2.6.0+cu126'"
       ]
      },
-     "execution_count": 2,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -38,12 +38,14 @@
    "id": "75acf7d8",
    "metadata": {},
    "source": [
-    "### Multi-dimensional"
+    "### Multi-dimensional\n",
+    "\n",
+    "![Tensor shape](https://cdn-images-1.medium.com/max/2000/1*_D5ZvufDS38WkhK9rK32hQ.jpeg)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "id": "0e82be1e",
    "metadata": {},
    "outputs": [
@@ -53,7 +55,7 @@
        "tensor(5)"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 2,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -66,7 +68,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "id": "7c239759",
    "metadata": {},
    "outputs": [
@@ -76,7 +78,7 @@
        "0"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -85,9 +87,18 @@
     "x.ndim"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "24ec3101",
+   "metadata": {},
+   "source": [
+    "![shapes](https://velog.velcdn.com/images/sangyun/post/ad3a0dfa-84cd-4b29-9a4e-9768b19c6df4/image.png)\n",
+    "![shapes](https://velog.velcdn.com/images/sangyun/post/accfee47-0d44-401c-a6b9-c4fff5822dcf/image.png)"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "id": "d176548d",
    "metadata": {},
    "outputs": [
@@ -97,7 +108,7 @@
        "torch.Size([])"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -108,7 +119,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "id": "07e03145",
    "metadata": {},
    "outputs": [
@@ -118,7 +129,7 @@
        "5"
       ]
      },
-     "execution_count": 6,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -129,7 +140,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "id": "41fcc46e",
    "metadata": {},
    "outputs": [
@@ -139,7 +150,7 @@
        "tensor([1, 2, 3])"
       ]
      },
-     "execution_count": 7,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -152,7 +163,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "id": "f9894c37",
    "metadata": {},
    "outputs": [
@@ -162,7 +173,7 @@
        "1"
       ]
      },
-     "execution_count": 8,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -173,7 +184,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "id": "7dc166eb",
    "metadata": {},
    "outputs": [
@@ -183,7 +194,7 @@
        "torch.Size([3])"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -195,7 +206,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "id": "2581817b",
    "metadata": {},
    "outputs": [
@@ -206,7 +217,7 @@
        "        [ 9, 10]])"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -220,7 +231,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "id": "46961042",
    "metadata": {},
    "outputs": [
@@ -230,7 +241,7 @@
        "2"
       ]
      },
-     "execution_count": 11,
+     "execution_count": 10,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -241,7 +252,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "id": "9669fda8",
    "metadata": {},
    "outputs": [
@@ -251,7 +262,7 @@
        "torch.Size([2, 2])"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -262,7 +273,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "id": "15297945",
    "metadata": {},
    "outputs": [
@@ -274,7 +285,7 @@
        "         [2, 4, 5]]])"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -289,7 +300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "id": "5bbed071",
    "metadata": {},
    "outputs": [
@@ -299,7 +310,7 @@
        "3"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -310,9 +321,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "id": "483d25c7",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([1, 3, 3])"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "TENSOR.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "c4e76ef2",
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -325,34 +357,13 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "TENSOR.shape"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 16,
-   "id": "c4e76ef2",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "torch.Size([1, 3, 3])"
-      ]
-     },
-     "execution_count": 16,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
    "source": [
     "TENSOR.size()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 16,
    "id": "b56abf50",
    "metadata": {},
    "outputs": [
@@ -364,7 +375,7 @@
        "        [6, 9]])"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -376,7 +387,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 17,
    "id": "cdd39ae8",
    "metadata": {},
    "outputs": [
@@ -391,7 +402,7 @@
        "        [9]])"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -403,7 +414,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "id": "adf1ab41",
    "metadata": {},
    "outputs": [
@@ -415,7 +426,7 @@
        "         [2., 4., 5.]]])"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -430,7 +441,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "id": "a368079f",
    "metadata": {},
    "outputs": [
@@ -440,7 +451,7 @@
        "torch.float32"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -451,20 +462,20 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 20,
    "id": "4d00ea95",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "(tensor([[0.9019, 0.8531],\n",
-       "         [0.9996, 0.5826]]),\n",
-       " tensor([[0.0682, 0.6102],\n",
-       "         [0.5610, 0.0305]]))"
+       "(tensor([[0.0440, 0.2059],\n",
+       "         [0.1639, 0.4233]]),\n",
+       " tensor([[0.1890, 0.7100],\n",
+       "         [0.9819, 0.5552]]))"
       ]
      },
-     "execution_count": 21,
+     "execution_count": 20,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -485,9 +496,31 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 21,
    "id": "aeed7a0a",
    "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([1, 2])"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "x=torch.tensor([1, 2, 3, 4, 5, 6])\n",
+    "x[0:2]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "721ce7eb",
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -500,28 +533,6 @@
      "output_type": "execute_result"
     }
    ],
-   "source": [
-    "x=torch.tensor([1, 2, 3, 4, 5, 6])\n",
-    "x[0:2]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 23,
-   "id": "721ce7eb",
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "tensor([1, 2])"
-      ]
-     },
-     "execution_count": 23,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
    "source": [
     "x=torch.tensor([1, 2, 3, 4, 5, 6])\n",
     "x[:2]"
@@ -529,7 +540,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 23,
    "id": "6423f4d2",
    "metadata": {},
    "outputs": [
@@ -539,7 +550,7 @@
        "tensor(6)"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 23,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -551,7 +562,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 24,
    "id": "0125386f",
    "metadata": {},
    "outputs": [
@@ -561,7 +572,7 @@
        "tensor([3, 4, 5, 6])"
       ]
      },
-     "execution_count": 25,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -573,7 +584,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 25,
    "id": "97373387",
    "metadata": {},
    "outputs": [
@@ -584,7 +595,7 @@
        "        [4, 5]])"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 25,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -604,7 +615,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 26,
    "id": "bba6b1b4",
    "metadata": {},
    "outputs": [
@@ -614,7 +625,7 @@
        "tensor([4, 5, 6])"
       ]
      },
-     "execution_count": 27,
+     "execution_count": 26,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -626,7 +637,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 27,
    "id": "12a96c84",
    "metadata": {},
    "outputs": [
@@ -636,7 +647,7 @@
        "tensor([3, 6, 9])"
       ]
      },
-     "execution_count": 28,
+     "execution_count": 27,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -648,7 +659,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 28,
    "id": "a0f73c88",
    "metadata": {},
    "outputs": [
@@ -658,7 +669,7 @@
        "tensor([[5, 6]])"
       ]
      },
-     "execution_count": 29,
+     "execution_count": 28,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -673,6 +684,32 @@
     "x[1:2, 1:3]  # tensor([[5, 6]])"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "485c115b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1 4\n",
+      "2 5\n",
+      "3 6\n"
+     ]
+    }
+   ],
+   "source": [
+    "# combine multiple iterables (like lists or tuples) element-wise \n",
+    "# into a single iterable of tuples.\n",
+    "a = torch.tensor([1, 2, 3])\n",
+    "b = torch.tensor([4, 5, 6])\n",
+    "\n",
+    "for x, y in zip(a, b):\n",
+    "    print(x.item(), y.item())"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "a3c1d8b5",
@@ -749,7 +786,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 54,
+   "execution_count": 33,
    "id": "cfa1dcae",
    "metadata": {},
    "outputs": [
@@ -759,7 +796,7 @@
        "tensor(6)"
       ]
      },
-     "execution_count": 54,
+     "execution_count": 33,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -771,7 +808,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 55,
+   "execution_count": 34,
    "id": "f27ae72f",
    "metadata": {},
    "outputs": [
@@ -781,7 +818,7 @@
        "tensor(3)"
       ]
      },
-     "execution_count": 55,
+     "execution_count": 34,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -793,19 +830,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 58,
+   "execution_count": 35,
    "id": "e10312d5",
    "metadata": {},
    "outputs": [],
    "source": [
     "test_outputs = torch.tensor([[2.5, 0.8, 1.3],  # Sample 1\n",
     "                            [0.4, 3.2, 1.9]]) # Sample 2\n",
-    "max_values, max_indices = torch.max(test_outputs,1)"
+    "max_values, max_indices = torch.max(test_outputs,1) # push alone the column"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 59,
+   "execution_count": 36,
    "id": "7f887d49",
    "metadata": {},
    "outputs": [
@@ -815,7 +852,7 @@
        "tensor([2.5000, 3.2000])"
       ]
      },
-     "execution_count": 59,
+     "execution_count": 36,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -826,7 +863,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 61,
+   "execution_count": 37,
    "id": "600af54b",
    "metadata": {},
    "outputs": [
@@ -836,7 +873,7 @@
        "tensor([0, 1])"
       ]
      },
-     "execution_count": 61,
+     "execution_count": 37,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -845,6 +882,29 @@
     "max_indices"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "f4ce3e53",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([2., 5.])"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "test_outputs = torch.tensor([[1, 2, 3],  # Sample 1\n",
+    "                            [4, 5, 6]], dtype=torch.float) # Sample 2\n",
+    "torch.mean(test_outputs,dim=1)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "id": "02a00747",
@@ -855,7 +915,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 33,
+   "execution_count": 39,
    "id": "45267f2f",
    "metadata": {},
    "outputs": [
@@ -868,7 +928,7 @@
        "         [7, 8]]))"
       ]
      },
-     "execution_count": 33,
+     "execution_count": 39,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -883,7 +943,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 34,
+   "execution_count": 40,
    "id": "193a7828",
    "metadata": {},
    "outputs": [
@@ -894,7 +954,7 @@
        "        [10, 12]])"
       ]
      },
-     "execution_count": 34,
+     "execution_count": 40,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -905,7 +965,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 41,
    "id": "1ce81689",
    "metadata": {},
    "outputs": [
@@ -916,7 +976,7 @@
        "        [21, 32]])"
       ]
      },
-     "execution_count": 35,
+     "execution_count": 41,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -928,7 +988,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 42,
    "id": "62f8cde3",
    "metadata": {},
    "outputs": [
@@ -938,7 +998,7 @@
        "tensor([11, 12, 13])"
       ]
      },
-     "execution_count": 36,
+     "execution_count": 42,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -953,7 +1013,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 43,
    "id": "2098ad78",
    "metadata": {},
    "outputs": [
@@ -964,7 +1024,7 @@
        "        [4, 5, 6]])"
       ]
      },
-     "execution_count": 37,
+     "execution_count": 43,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -977,7 +1037,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 44,
    "id": "883321f8",
    "metadata": {},
    "outputs": [
@@ -989,7 +1049,7 @@
        "        [5, 6]])"
       ]
      },
-     "execution_count": 38,
+     "execution_count": 44,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1000,7 +1060,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 39,
+   "execution_count": 45,
    "id": "9ceace9b",
    "metadata": {},
    "outputs": [
@@ -1010,7 +1070,7 @@
        "tensor([False,  True,  True, False,  True, False])"
       ]
      },
-     "execution_count": 39,
+     "execution_count": 45,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1022,7 +1082,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 40,
+   "execution_count": 46,
    "id": "96ea0d2f",
    "metadata": {},
    "outputs": [
@@ -1032,7 +1092,7 @@
        "tensor([ True, False,  True,  True, False, False])"
       ]
      },
-     "execution_count": 40,
+     "execution_count": 46,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1044,7 +1104,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 41,
+   "execution_count": 47,
    "id": "c1d9f060",
    "metadata": {},
    "outputs": [
@@ -1054,7 +1114,7 @@
        "tensor([False, False,  True, False, False, False])"
       ]
      },
-     "execution_count": 41,
+     "execution_count": 47,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1065,7 +1125,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 42,
+   "execution_count": 48,
    "id": "796d977f",
    "metadata": {},
    "outputs": [
@@ -1075,7 +1135,7 @@
        "tensor(1)"
       ]
      },
-     "execution_count": 42,
+     "execution_count": 48,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1086,7 +1146,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 43,
+   "execution_count": 49,
    "id": "60402427",
    "metadata": {},
    "outputs": [
@@ -1096,7 +1156,7 @@
        "tensor(1)"
       ]
      },
-     "execution_count": 43,
+     "execution_count": 49,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1119,7 +1179,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 50,
    "id": "2a3fd4ae",
    "metadata": {},
    "outputs": [
@@ -1129,7 +1189,7 @@
        "tensor([1, 2, 3])"
       ]
      },
-     "execution_count": 44,
+     "execution_count": 50,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1142,7 +1202,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 51,
    "id": "df247bd3",
    "metadata": {},
    "outputs": [
@@ -1152,7 +1212,7 @@
        "array([1, 2, 3])"
       ]
      },
-     "execution_count": 45,
+     "execution_count": 51,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1164,7 +1224,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 52,
    "id": "9ada07ab",
    "metadata": {},
    "outputs": [
@@ -1174,7 +1234,7 @@
        "tensor([1, 2, 3])"
       ]
      },
-     "execution_count": 46,
+     "execution_count": 52,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1194,7 +1254,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 53,
    "id": "30c9ea9f",
    "metadata": {},
    "outputs": [
@@ -1204,7 +1264,7 @@
        "True"
       ]
      },
-     "execution_count": 47,
+     "execution_count": 53,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1217,7 +1277,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 54,
    "id": "dd523b3e",
    "metadata": {},
    "outputs": [
@@ -1227,7 +1287,7 @@
        "'cuda'"
       ]
      },
-     "execution_count": 48,
+     "execution_count": 54,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1240,7 +1300,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 55,
    "id": "11d1a029",
    "metadata": {},
    "outputs": [
@@ -1257,7 +1317,7 @@
        "tensor([1, 2, 3], device='cuda:0')"
       ]
      },
-     "execution_count": 49,
+     "execution_count": 55,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1276,7 +1336,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 50,
+   "execution_count": 56,
    "id": "db5249d0",
    "metadata": {},
    "outputs": [
@@ -1284,7 +1344,7 @@
      "name": "stderr",
      "output_type": "stream",
      "text": [
-      "C:\\Users\\Weife\\AppData\\Local\\Temp\\ipykernel_154616\\3540074575.py:6: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
+      "C:\\Users\\Weife\\AppData\\Local\\Temp\\ipykernel_68020\\3540074575.py:6: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).\n",
       "  y = torch.tensor(x, device=device)  # directly create a tensor on GPU\n"
      ]
     }
diff --git a/lectures/09_multiclass_classification_cnn_n_to_n/01_MNIST.ipynb b/lectures/09_multiclass_classification_cnn_n_to_n/01_MNIST.ipynb
index 84dc3e1..920c682 100644
--- a/lectures/09_multiclass_classification_cnn_n_to_n/01_MNIST.ipynb
+++ b/lectures/09_multiclass_classification_cnn_n_to_n/01_MNIST.ipynb
@@ -1,31 +1,19 @@
 {
  "cells": [
   {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "8ce2d850",
+   "cell_type": "markdown",
+   "id": "e0f425f2",
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Epoch 1, Loss: 0.1675, Accuracy: 95.05%\n",
-      "Epoch 2, Loss: 0.0710, Accuracy: 97.94%\n",
-      "Epoch 3, Loss: 0.0518, Accuracy: 98.42%\n",
-      "Epoch 4, Loss: 0.0462, Accuracy: 98.64%\n",
-      "Epoch 5, Loss: 0.0384, Accuracy: 98.87%\n",
-      "Epoch 6, Loss: 0.0336, Accuracy: 99.00%\n",
-      "Epoch 7, Loss: 0.0323, Accuracy: 99.06%\n",
-      "Epoch 8, Loss: 0.0260, Accuracy: 99.22%\n",
-      "Epoch 9, Loss: 0.0254, Accuracy: 99.19%\n",
-      "Epoch 10, Loss: 0.0226, Accuracy: 99.27%\n",
-      "\n",
-      "Test Accuracy: 99.34%\n",
-      "Training complete. Plots saved as 'mnist_training_metrics.png', 'mnist_confusion_matrix.png', and 'mnist_sample_predictions.png'\n"
-     ]
-    }
-   ],
+   "source": [
+    "### Load dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "03bfb9c3",
+   "metadata": {},
+   "outputs": [],
    "source": [
     "import torch  # PyTorch library for tensor operations and deep learning\n",
     "import torch.nn as nn  # Neural network modules and layers\n",
@@ -76,7 +64,56 @@
     "# Define class labels for MNIST (digits 0-9)\n",
     "classes = tuple(str(i) for i in range(10))\n",
     "\n",
-    "# Define CNN architecture\n",
+    "# Define CNN architecture"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e1f37048",
+   "metadata": {},
+   "source": [
+    "### (Optional) Debugging trainloader\n",
+    "\n",
+    "- trainloader is an instance of torch.utils.data.DataLoader, a PyTorch utility that provides an efficient way to iterate over a dataset (e.g., MNIST) in manageable chunks (batches).\n",
+    "- trainloader is iterable in PyTorch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "e21fde9f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch.Size([64, 1, 28, 28]) torch.Size([64])\n"
+     ]
+    }
+   ],
+   "source": [
+    "for data in trainloader:\n",
+    "    inputs, labels = data\n",
+    "    print(inputs.shape, labels.shape)  # Should print: torch.Size([64, 1, 28, 28]) torch.Size([64])\n",
+    "    break"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4328b140",
+   "metadata": {},
+   "source": [
+    "### Create a training model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4f5d7e6e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
     "class Net(nn.Module):\n",
     "    def __init__(self):\n",
     "        super(Net, self).__init__()\n",
@@ -127,8 +164,71 @@
     "\n",
     "# Initialize model and move to appropriate device (GPU if available, else CPU)\n",
     "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
-    "model = Net().to(device)\n",
-    "\n",
+    "model = Net().to(device)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "46fa8f0f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Net(\n",
+       "  (conv1): Conv2d(1, 32, kernel_size=(5, 5), stride=(1, 1))\n",
+       "  (conv2): Conv2d(32, 64, kernel_size=(5, 5), stride=(1, 1))\n",
+       "  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)\n",
+       "  (bn1): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+       "  (bn2): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)\n",
+       "  (fc1): Linear(in_features=1024, out_features=128, bias=True)\n",
+       "  (fc2): Linear(in_features=128, out_features=10, bias=True)\n",
+       "  (dropout): Dropout(p=0.5, inplace=False)\n",
+       ")"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0b8f7a77",
+   "metadata": {},
+   "source": [
+    "### Training"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "068a0766",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1, Loss: 0.1610, Accuracy: 95.22%\n",
+      "Epoch 2, Loss: 0.0693, Accuracy: 97.90%\n",
+      "Epoch 3, Loss: 0.0542, Accuracy: 98.35%\n",
+      "Epoch 4, Loss: 0.0443, Accuracy: 98.68%\n",
+      "Epoch 5, Loss: 0.0401, Accuracy: 98.78%\n",
+      "Epoch 6, Loss: 0.0348, Accuracy: 98.94%\n",
+      "Epoch 7, Loss: 0.0279, Accuracy: 99.12%\n",
+      "Epoch 8, Loss: 0.0279, Accuracy: 99.14%\n",
+      "Epoch 9, Loss: 0.0249, Accuracy: 99.18%\n",
+      "Epoch 10, Loss: 0.0197, Accuracy: 99.38%\n"
+     ]
+    }
+   ],
+   "source": [
     "# Define loss function\n",
     "# - CrossEntropyLoss: Combines log softmax and negative log likelihood loss\n",
     "criterion = nn.CrossEntropyLoss()\n",
@@ -173,28 +273,27 @@
     "    epoch_acc = 100 * correct / total\n",
     "    train_losses.append(epoch_loss)\n",
     "    train_accuracies.append(epoch_acc)\n",
-    "    print(f\"Epoch {epoch + 1}, Loss: {epoch_loss:.4f}, Accuracy: {epoch_acc:.2f}%\")\n",
-    "\n",
-    "# Evaluate model on test set\n",
-    "model.eval()  # Set model to evaluation mode\n",
-    "correct = 0\n",
-    "total = 0\n",
-    "all_preds = []  # Store predictions for confusion matrix\n",
-    "all_labels = []  # Store true labels\n",
-    "with torch.no_grad():  # Disable gradient computation for efficiency\n",
-    "    for data in testloader:\n",
-    "        images, labels = data[0].to(device), data[1].to(device)\n",
-    "        outputs = model(images)\n",
-    "        _, predicted = torch.max(outputs.data, 1)\n",
-    "        total += labels.size(0)\n",
-    "        correct += (predicted == labels).sum().item()\n",
-    "        all_preds.extend(predicted.cpu().numpy())\n",
-    "        all_labels.extend(labels.cpu().numpy())\n",
-    "\n",
-    "# Calculate and print test accuracy\n",
-    "test_accuracy = 100 * correct / total\n",
-    "print(f\"\\nTest Accuracy: {test_accuracy:.2f}%\")\n",
-    "\n",
+    "    print(f\"Epoch {epoch + 1}, Loss: {epoch_loss:.4f}, Accuracy: {epoch_acc:.2f}%\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "e6b4ba69",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
     "# Plot training metrics (loss and accuracy)\n",
     "plt.figure(figsize=(12, 4))\n",
     "\n",
@@ -215,9 +314,84 @@
     "plt.legend()\n",
     "\n",
     "plt.tight_layout()\n",
-    "plt.savefig('mnist_training_metrics.png')  # Save the plot\n",
+    "plt.show()\n",
+    "# plt.savefig('mnist_training_metrics.png')  # Save the plot\n",
     "plt.close()\n",
     "\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "771d4e48",
+   "metadata": {},
+   "source": [
+    "### Evaluate model on test set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "b6ba9b0e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Test Accuracy: 99.37%\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Evaluate model on test set\n",
+    "model.eval()  # Set model to evaluation mode\n",
+    "correct = 0\n",
+    "total = 0\n",
+    "all_preds = []  # Store predictions for confusion matrix\n",
+    "all_labels = []  # Store true labels\n",
+    "with torch.no_grad():  # Disable gradient computation for efficiency\n",
+    "    for data in testloader:\n",
+    "        images, labels = data[0].to(device), data[1].to(device)\n",
+    "        outputs = model(images)\n",
+    "        _, predicted = torch.max(outputs.data, 1)\n",
+    "        total += labels.size(0)\n",
+    "        correct += (predicted == labels).sum().item()\n",
+    "        all_preds.extend(predicted.cpu().numpy())\n",
+    "        all_labels.extend(labels.cpu().numpy())\n",
+    "\n",
+    "# Calculate and print test accuracy\n",
+    "test_accuracy = 100 * correct / total\n",
+    "print(f\"\\nTest Accuracy: {test_accuracy:.2f}%\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "58ca97c3",
+   "metadata": {},
+   "source": [
+    "### Plot confusion matrix to visualize class-wise performance"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "36d089b4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x800 with 2 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
     "# Plot confusion matrix to visualize class-wise performance\n",
     "cm = confusion_matrix(all_labels, all_preds)\n",
     "plt.figure(figsize=(10, 8))\n",
@@ -226,9 +400,44 @@
     "plt.title('Confusion Matrix')\n",
     "plt.xlabel('Predicted')\n",
     "plt.ylabel('True')\n",
-    "plt.savefig('mnist_confusion_matrix.png')  # Save the plot\n",
-    "plt.close()\n",
-    "\n",
+    "plt.show()\n",
+    "# plt.savefig('mnist_confusion_matrix.png')  # Save the plot\n",
+    "plt.close()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "7875d6f8",
+   "metadata": {},
+   "source": [
+    "### Display sample test images with predictions"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "8ce2d850",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x600 with 8 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Training complete. Plots saved as 'mnist_training_metrics.png', 'mnist_confusion_matrix.png', and 'mnist_sample_predictions.png'\n"
+     ]
+    }
+   ],
+   "source": [
     "# Function to unnormalize and display MNIST images\n",
     "def imshow(img):\n",
     "    img = img * 0.3081 + 0.1307  # Unnormalize (reverse mean/std normalization)\n",
@@ -248,12 +457,22 @@
     "    plt.imshow(imshow(images[i].cpu()), cmap='gray')  # Display grayscale image\n",
     "    plt.title(f'Pred: {classes[predicted[i]]}\\nTrue: {classes[labels[i]]}')\n",
     "    plt.axis('off')\n",
-    "plt.savefig('mnist_sample_predictions.png')  # Save the plot\n",
+    "\n",
+    "plt.show()\n",
+    "#plt.savefig('mnist_sample_predictions.png')  # Save the plot\n",
     "plt.close()\n",
     "\n",
     "# Print completion message\n",
     "print(\"Training complete. Plots saved as 'mnist_training_metrics.png', 'mnist_confusion_matrix.png', and 'mnist_sample_predictions.png'\")"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b66c4356",
+   "metadata": {},
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {
diff --git a/lectures/10_word_embedding/0_word_embedding.pptx b/lectures/10_word_embedding/0_word_embedding.pptx
new file mode 100644
index 0000000..018d56e
Binary files /dev/null and b/lectures/10_word_embedding/0_word_embedding.pptx differ
diff --git a/lectures/10_word_embedding/0_word_embeddings.ipynb b/lectures/10_word_embedding/0_word_embeddings.ipynb
new file mode 100644
index 0000000..d7cddd4
--- /dev/null
+++ b/lectures/10_word_embedding/0_word_embeddings.ipynb
@@ -0,0 +1,741 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## BERT input tokenization"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 48,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Original text: The king rules the kingdom\n",
+            "Tokens:       ['[CLS]', 'the', 'king', 'rules', 'the', 'kingdom', '[SEP]']\n",
+            "Token IDs:    [101, 1996, 2332, 3513, 1996, 2983, 102]\n"
+          ]
+        }
+      ],
+      "source": [
+        "from transformers import AutoTokenizer\n",
+        "\n",
+        "def tokenize_text(text, model_name='bert-base-uncased'):\n",
+        "    # Load pre-trained tokenizer\n",
+        "    tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+        "    \n",
+        "    # Tokenize the input text\n",
+        "    inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)\n",
+        "    \n",
+        "    # Extract token IDs and convert to tokens\n",
+        "    token_ids = inputs['input_ids'][0]\n",
+        "    tokens = tokenizer.convert_ids_to_tokens(token_ids)\n",
+        "    \n",
+        "    return tokens, token_ids\n",
+        "\n",
+        "# Example\n",
+        "text = \"The king rules the kingdom\"\n",
+        "tokens, token_ids = tokenize_text(text)\n",
+        "\n",
+        "print(\"Original text:\", text)\n",
+        "print(\"Tokens:      \", tokens)\n",
+        "print(\"Token IDs:   \", token_ids.tolist())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Calcuate Word Embeddings"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 49,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "torch.Size([7, 768])\n",
+            "Tokens and their embeddings (first 5 dimensions):\n",
+            "[CLS]: [-0.29844123  0.6102891   0.15138927 -0.06507589 -0.44881746]...\n",
+            "the: [-0.54813766  0.0798662  -0.1852346   0.21140489 -0.09343444]...\n",
+            "king: [ 0.09419857  0.09978478  0.60134786 -0.02520893 -0.02910186]...\n",
+            "rules: [ 0.03675649  0.2432631  -0.2417559  -0.2521967  -0.08357717]...\n",
+            "the: [-0.4276377  -0.2732732   0.3628907  -0.5024754   0.15975913]...\n",
+            "kingdom: [ 0.00768744 -0.48735484  0.2892718   0.12761931  0.2640031 ]...\n",
+            "[SEP]: [ 0.80087405  0.08718775 -0.2546647   0.5996189  -0.65110075]...\n"
+          ]
+        }
+      ],
+      "source": [
+        "import torch\n",
+        "from transformers import AutoTokenizer, AutoModel\n",
+        "\n",
+        "def get_token_embeddings(text, model_name='bert-base-uncased'):\n",
+        "    # Load pre-trained tokenizer and model\n",
+        "    tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+        "    model = AutoModel.from_pretrained(model_name)\n",
+        "    \n",
+        "    # Tokenize input text\n",
+        "    inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)\n",
+        "    tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0])\n",
+        "    \n",
+        "    # Get model outputs (embeddings)\n",
+        "    with torch.no_grad():\n",
+        "        # unpack a dictionary and pass its key-value pairs \n",
+        "        # as keyword arguments to a function \n",
+        "        outputs = model(**inputs)\n",
+        "    \n",
+        "    # Extract embeddings from the last hidden state\n",
+        "    embeddings = outputs.last_hidden_state[0]  \n",
+        "    print(embeddings.shape)\n",
+        "    # Shape: (sequence_length, 768)\n",
+        "    \n",
+        "    return tokens, embeddings\n",
+        "\n",
+        "# Example: Getting embeddings for tokens\n",
+        "text = \"The king rules the kingdom\"\n",
+        "tokens, embeddings = get_token_embeddings(text)\n",
+        "print(\"Tokens and their embeddings (first 5 dimensions):\")\n",
+        "for token, emb in zip(tokens, embeddings):\n",
+        "    print(f\"{token}: {emb[:5].numpy()}...\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Magnitude-normalized word embeddings"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 56,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "image/png": "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",
+            "text/plain": [
+              "<Figure size 1200x600 with 2 Axes>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Cosine Similarity (Original): Approximately 0.999866\n",
+            "Cosine Similarity (Magnitude-Normalized Vectors): Approximately 0.9994\n"
+          ]
+        }
+      ],
+      "source": [
+        "import matplotlib.pyplot as plt\n",
+        "import numpy as np\n",
+        "\n",
+        "# Original data\n",
+        "A_original = np.array([170, 70])\n",
+        "B_original = np.array([180, 80])\n",
+        "\n",
+        "# Magnitude-normalized data\n",
+        "A_norm_mag = np.array([170/np.linalg.norm(A_original), 70/np.linalg.norm(A_original)])\n",
+        "B_norm_mag = np.array([180/np.linalg.norm(B_original), 80/np.linalg.norm(B_original)])\n",
+        "\n",
+        "# Plotting function\n",
+        "def plot_vectors_magnitude_norm(v1_orig, v2_orig, v1_norm, v2_norm):\n",
+        "    plt.figure(figsize=(12, 6))\n",
+        "\n",
+        "    # Plot Original Vectors\n",
+        "    plt.subplot(1, 2, 1)\n",
+        "    plt.quiver(0, 0, v1_orig[0], v1_orig[1], angles='xy', scale_units='xy', scale=1, color='r', label='A')\n",
+        "    plt.quiver(0, 0, v2_orig[0], v2_orig[1], angles='xy', scale_units='xy', scale=1, color='b', label='B')\n",
+        "    plt.xlabel('Height')\n",
+        "    plt.ylabel('Weight')\n",
+        "    plt.title('Original Vectors')\n",
+        "    plt.xlim(0, max(max(v1_orig), max(v2_orig)) * 1.1)\n",
+        "    plt.ylim(0, max(max(v1_orig), max(v2_orig)) * 1.1)\n",
+        "    plt.legend()\n",
+        "    plt.grid(True)\n",
+        "\n",
+        "    # Plot Magnitude-Normalized Vectors\n",
+        "    plt.subplot(1, 2, 2)\n",
+        "    plt.quiver(0, 0, v1_norm[0], v1_norm[1], angles='xy', scale_units='xy', scale=1, color='r', label='A_norm')\n",
+        "    plt.quiver(0, 0, v2_norm[0], v2_norm[1], angles='xy', scale_units='xy', scale=1, color='b', label='B_norm')\n",
+        "    plt.xlabel('Normalized Height')\n",
+        "    plt.ylabel('Normalized Weight')\n",
+        "    plt.title('Magnitude-Normalized Vectors (Unit Vectors)')\n",
+        "    plt.xlim(-0.1, 1.1)\n",
+        "    plt.ylim(-0.1, 1.1)\n",
+        "    plt.legend()\n",
+        "    plt.grid(True)\n",
+        "\n",
+        "    plt.tight_layout()\n",
+        "    plt.show()\n",
+        "\n",
+        "# Plotting\n",
+        "plot_vectors_magnitude_norm(A_original, B_original, A_norm_mag, B_norm_mag)\n",
+        "\n",
+        "print(f\"Cosine Similarity (Original): Approximately {0.999866}\")\n",
+        "print(f\"Cosine Similarity (Magnitude-Normalized Vectors): Approximately {0.9994}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Cosine Similarity between words:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 50,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Cosine Similarity between words:\n",
+            "\n",
+            "the:\n",
+            "  the: 1.0000\n",
+            "  king: 0.5347\n",
+            "  rules: 0.6333\n",
+            "  kingdom: 0.4193\n",
+            "  and: 0.6179\n",
+            "  queen: 0.5356\n",
+            "  govern: 0.5052\n",
+            "  ##s: 0.6915\n",
+            "\n",
+            "king:\n",
+            "  the: 0.5347\n",
+            "  king: 1.0000\n",
+            "  rules: 0.5543\n",
+            "  kingdom: 0.7628\n",
+            "  and: 0.4104\n",
+            "  queen: 0.6944\n",
+            "  govern: 0.4572\n",
+            "  ##s: 0.4637\n",
+            "\n",
+            "rules:\n",
+            "  the: 0.6333\n",
+            "  king: 0.5543\n",
+            "  rules: 1.0000\n",
+            "  kingdom: 0.5100\n",
+            "  and: 0.5204\n",
+            "  queen: 0.5216\n",
+            "  govern: 0.8282\n",
+            "  ##s: 0.7327\n",
+            "\n",
+            "kingdom:\n",
+            "  the: 0.4193\n",
+            "  king: 0.7628\n",
+            "  rules: 0.5100\n",
+            "  kingdom: 1.0000\n",
+            "  and: 0.3829\n",
+            "  queen: 0.5706\n",
+            "  govern: 0.4558\n",
+            "  ##s: 0.4068\n",
+            "\n",
+            "and:\n",
+            "  the: 0.6179\n",
+            "  king: 0.4104\n",
+            "  rules: 0.5204\n",
+            "  kingdom: 0.3829\n",
+            "  and: 1.0000\n",
+            "  queen: 0.3631\n",
+            "  govern: 0.4269\n",
+            "  ##s: 0.5884\n",
+            "\n",
+            "queen:\n",
+            "  the: 0.5356\n",
+            "  king: 0.6944\n",
+            "  rules: 0.5216\n",
+            "  kingdom: 0.5706\n",
+            "  and: 0.3631\n",
+            "  queen: 1.0000\n",
+            "  govern: 0.4541\n",
+            "  ##s: 0.4744\n",
+            "\n",
+            "govern:\n",
+            "  the: 0.5052\n",
+            "  king: 0.4572\n",
+            "  rules: 0.8282\n",
+            "  kingdom: 0.4558\n",
+            "  and: 0.4269\n",
+            "  queen: 0.4541\n",
+            "  govern: 1.0000\n",
+            "  ##s: 0.5646\n",
+            "\n",
+            "##s:\n",
+            "  the: 0.6915\n",
+            "  king: 0.4637\n",
+            "  rules: 0.7327\n",
+            "  kingdom: 0.4068\n",
+            "  and: 0.5884\n",
+            "  queen: 0.4744\n",
+            "  govern: 0.5646\n",
+            "  ##s: 1.0000\n"
+          ]
+        }
+      ],
+      "source": [
+        "import torch\n",
+        "import numpy as np\n",
+        "from transformers import AutoTokenizer, AutoModel\n",
+        "from sklearn.metrics.pairwise import cosine_similarity\n",
+        "\n",
+        "def get_word_embeddings(text, model_name='bert-base-uncased'):\n",
+        "    tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+        "    model = AutoModel.from_pretrained(model_name)\n",
+        "    inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)\n",
+        "    tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0])\n",
+        "    with torch.no_grad():\n",
+        "        outputs = model(**inputs)\n",
+        "    embeddings = outputs.last_hidden_state[0]\n",
+        "    \n",
+        "    word_emb_dict = {}\n",
+        "    for token, emb in zip(tokens, embeddings):\n",
+        "        if token not in ['[CLS]', '[SEP]']:\n",
+        "            word_emb_dict[token] = emb\n",
+        "    return word_emb_dict\n",
+        "\n",
+        "def compute_similarity(word_emb_dict):\n",
+        "    words = list(word_emb_dict.keys())\n",
+        "    embeddings = torch.stack([word_emb_dict[word] for word in words]).numpy()\n",
+        "    similarities = cosine_similarity(embeddings)\n",
+        "    \n",
+        "    relation_matrix = {}\n",
+        "    for i, word1 in enumerate(words):\n",
+        "        relation_matrix[word1] = {}\n",
+        "        for j, word2 in enumerate(words):\n",
+        "            relation_matrix[word1][word2] = similarities[i][j]\n",
+        "    return relation_matrix\n",
+        "\n",
+        "# Example: Measuring similarity between words\n",
+        "if __name__ == \"__main__\":\n",
+        "    text = \"The king rules the kingdom and the queen governs\"\n",
+        "    word_emb_dict = get_word_embeddings(text)\n",
+        "    relation_matrix = compute_similarity(word_emb_dict)\n",
+        "    print(\"Cosine Similarity between words:\")\n",
+        "    for word1 in relation_matrix:\n",
+        "        print(f\"\\n{word1}:\")\n",
+        "        for word2, similarity in relation_matrix[word1].items():\n",
+        "            print(f\"  {word2}: {similarity:.4f}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Visualizing Cosine Similarity between words"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 51,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Heatmap saved as 'similarity_heatmap.png'\n"
+          ]
+        },
+        {
+          "data": {
+            "image/png": "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",
+            "text/plain": [
+              "<Figure size 1000x800 with 2 Axes>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "import torch\n",
+        "import numpy as np\n",
+        "import matplotlib.pyplot as plt\n",
+        "from transformers import AutoTokenizer, AutoModel\n",
+        "from sklearn.metrics.pairwise import cosine_similarity\n",
+        "\n",
+        "def get_word_embeddings(text, model_name='bert-base-uncased'):\n",
+        "    tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+        "    model = AutoModel.from_pretrained(model_name)\n",
+        "    inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)\n",
+        "    tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0])\n",
+        "    with torch.no_grad():\n",
+        "        outputs = model(**inputs)\n",
+        "    embeddings = outputs.last_hidden_state[0]\n",
+        "    \n",
+        "    word_emb_dict = {}\n",
+        "    for token, emb in zip(tokens, embeddings):\n",
+        "        if token not in ['[CLS]', '[SEP]']:\n",
+        "            if token == 'the' and token in word_emb_dict:\n",
+        "                word_emb_dict[f'the_{len([k for k in word_emb_dict.keys() if k.startswith(\"the_\")])+1}'] = emb\n",
+        "            elif token not in word_emb_dict:\n",
+        "                word_emb_dict[token] = emb\n",
+        "    return word_emb_dict\n",
+        "\n",
+        "def compute_similarity(word_emb_dict):\n",
+        "    words = list(word_emb_dict.keys())\n",
+        "    embeddings = torch.stack([word_emb_dict[word] for word in words]).numpy()\n",
+        "    similarities = cosine_similarity(embeddings)\n",
+        "    return words, similarities\n",
+        "\n",
+        "def visualize_similarity(words, similarities):\n",
+        "    plt.figure(figsize=(10, 8))\n",
+        "    plt.imshow(similarities, cmap='viridis', interpolation='nearest')\n",
+        "    plt.colorbar(label='Cosine Similarity')\n",
+        "    plt.xticks(np.arange(len(words)), words, rotation=45)\n",
+        "    plt.yticks(np.arange(len(words)), words)\n",
+        "    plt.title('Cosine Similarity Between Word Embeddings')\n",
+        "    plt.tight_layout()\n",
+        "    \n",
+        "    # Save the plot\n",
+        "    # plt.savefig('similarity_heatmap.png')\n",
+        "\n",
+        "# Example: Visualizing similarity\n",
+        "if __name__ == \"__main__\":\n",
+        "    text = \"The king rules the kingdom and the queen governs\"\n",
+        "    word_emb_dict = get_word_embeddings(text)\n",
+        "    words, similarities = compute_similarity(word_emb_dict)\n",
+        "    visualize_similarity(words, similarities)\n",
+        "    print(\"Heatmap saved as 'similarity_heatmap.png'\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## Word Analogy: king - man + woman ≈ queen\n",
+        "- Similarity between (king - man + woman) and queen"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 52,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Word Analogy: king - man + woman ≈ queen\n",
+            "Similarity between (king - man + woman) and queen: 0.7002\n"
+          ]
+        }
+      ],
+      "source": [
+        "import torch\n",
+        "import numpy as np\n",
+        "from transformers import AutoTokenizer, AutoModel\n",
+        "from sklearn.metrics.pairwise import cosine_similarity\n",
+        "\n",
+        "def get_word_embeddings(texts, target_words, model_name='bert-base-uncased'):\n",
+        "    tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
+        "    model = AutoModel.from_pretrained(model_name)\n",
+        "    \n",
+        "    word_emb_dict = {}\n",
+        "    for text in texts:\n",
+        "        inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)\n",
+        "        tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0])\n",
+        "        with torch.no_grad():\n",
+        "            outputs = model(**inputs)\n",
+        "        embeddings = outputs.last_hidden_state[0]\n",
+        "        \n",
+        "        for token, emb in zip(tokens, embeddings):\n",
+        "            if token in target_words and token not in word_emb_dict:\n",
+        "                word_emb_dict[token] = emb\n",
+        "    \n",
+        "    return word_emb_dict\n",
+        "\n",
+        "# Example: Demonstrating word analogy\n",
+        "if __name__ == \"__main__\":\n",
+        "    texts = [\n",
+        "        \"The king rules the kingdom\",\n",
+        "        \"The queen governs the realm\",\n",
+        "        \"The man works in the city\",\n",
+        "        \"The woman lives in the town\"\n",
+        "    ]\n",
+        "    target_words = ['king', 'queen', 'man', 'woman']\n",
+        "    \n",
+        "    # Get embeddings for target words\n",
+        "    word_emb_dict = get_word_embeddings(texts, target_words)\n",
+        "    \n",
+        "    # Perform analogy: king - man + woman ≈ queen\n",
+        "    king_emb = word_emb_dict['king']\n",
+        "    man_emb = word_emb_dict['man']\n",
+        "    woman_emb = word_emb_dict['woman']\n",
+        "    queen_emb = word_emb_dict['queen']\n",
+        "    \n",
+        "    analogy_vector = king_emb - man_emb + woman_emb\n",
+        "    analogy_similarity = cosine_similarity(analogy_vector.unsqueeze(0).numpy(), \n",
+        "                                        queen_emb.unsqueeze(0).numpy())[0][0]\n",
+        "    \n",
+        "    print(\"Word Analogy: king - man + woman ≈ queen\")\n",
+        "    print(f\"Similarity between (king - man + woman) and queen: {analogy_similarity:.4f}\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "## 3D Word Analogy Visualization: king - man + woman ≈ queen"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 60,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "image/png": "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",
+            "text/plain": [
+              "<Figure size 1000x800 with 1 Axes>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "# Re-run everything after kernel reset\n",
+        "# Re-import required packages after code execution state reset\n",
+        "import torch\n",
+        "import matplotlib.pyplot as plt\n",
+        "from sklearn.decomposition import PCA\n",
+        "from mpl_toolkits.mplot3d import Axes3D # Import for 3D plotting\n",
+        "from transformers import AutoTokenizer, AutoModel\n",
+        "\n",
+        "# Define text and target words\n",
+        "texts = [\n",
+        "    \"The king rules the kingdom\",\n",
+        "    \"The queen governs the realm\",\n",
+        "    \"The man works in the city\",\n",
+        "    \"The woman lives in the town\"\n",
+        "]\n",
+        "target_words = ['king', 'queen', 'man', 'woman']\n",
+        "\n",
+        "# Load tokenizer and model\n",
+        "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
+        "model = AutoModel.from_pretrained('bert-base-uncased')\n",
+        "\n",
+        "# Extract embeddings for target words\n",
+        "word_emb_dict = {}\n",
+        "for text in texts:\n",
+        "    inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)\n",
+        "    tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0])\n",
+        "    with torch.no_grad():\n",
+        "        outputs = model(**inputs)\n",
+        "    embeddings = outputs.last_hidden_state[0]\n",
+        "\n",
+        "    for token, emb in zip(tokens, embeddings):\n",
+        "        # We only want the first occurrence of each target word to ensure consistent embedding\n",
+        "        if token in target_words and token not in word_emb_dict:\n",
+        "            word_emb_dict[token] = emb\n",
+        "\n",
+        "# Ensure all target words were found\n",
+        "if len(word_emb_dict) < len(target_words):\n",
+        "    print(f\"Warning: Not all target words were found. Found: {list(word_emb_dict.keys())}\")\n",
+        "    # Handle missing words, e.g., by skipping the analogy or using a placeholder\n",
+        "    # For this example, we'll stop if a key word for the analogy is missing.\n",
+        "    if 'king' not in word_emb_dict or 'man' not in word_emb_dict or \\\n",
+        "       'woman' not in word_emb_dict or 'queen' not in word_emb_dict:\n",
+        "        print(\"Essential words for the analogy are missing. Exiting.\")\n",
+        "        exit()\n",
+        "\n",
+        "\n",
+        "# Prepare vectors for analogy\n",
+        "king_emb = word_emb_dict['king']\n",
+        "man_emb = word_emb_dict['man']\n",
+        "woman_emb = word_emb_dict['woman']\n",
+        "queen_emb = word_emb_dict['queen']\n",
+        "\n",
+        "# Compute analogy vector\n",
+        "analogy_vector = king_emb - man_emb + woman_emb\n",
+        "\n",
+        "# Reduce dimensions using PCA\n",
+        "vectors = torch.stack([king_emb, man_emb, woman_emb, queen_emb, analogy_vector])\n",
+        "labels = ['king', 'man', 'woman', 'queen', 'king - man + woman']\n",
+        "\n",
+        "# Change n_components to 3 for 3D visualization\n",
+        "pca = PCA(n_components=3)\n",
+        "reduced = pca.fit_transform(vectors.detach().numpy()) # Use .detach().numpy() for tensors\n",
+        "\n",
+        "# Plot\n",
+        "fig = plt.figure(figsize=(10, 8)) # Adjusted figure size for 3D\n",
+        "ax = fig.add_subplot(111, projection='3d') # Create a 3D subplot\n",
+        "\n",
+        "for i, label in enumerate(labels):\n",
+        "    x, y, z = reduced[i]\n",
+        "    ax.scatter(x, y, z, s=50) # s is the marker size\n",
+        "    ax.text(x + 0.01, y + 0.01, z + 0.01, label, fontsize=12)\n",
+        "\n",
+        "ax.set_title(\"3D Word Analogy Visualization: king - man + woman ≈ queen\")\n",
+        "ax.set_xlabel(\"PCA Component 1\")\n",
+        "ax.set_ylabel(\"PCA Component 2\")\n",
+        "ax.set_zlabel(\"PCA Component 3\")\n",
+        "plt.grid(True)\n",
+        "plt.tight_layout()\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 61,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "image/png": "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",
+            "text/plain": [
+              "<Figure size 1200x1000 with 1 Axes>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "# Re-run everything after kernel reset\n",
+        "# Re-import required packages after code execution state reset\n",
+        "import torch\n",
+        "import matplotlib.pyplot as plt\n",
+        "from sklearn.decomposition import PCA\n",
+        "from mpl_toolkits.mplot3d import Axes3D # Import for 3D plotting\n",
+        "from transformers import AutoTokenizer, AutoModel\n",
+        "\n",
+        "# Define text and target words\n",
+        "texts = [\n",
+        "    \"The king rules the kingdom\",\n",
+        "    \"The queen governs the realm\",\n",
+        "    \"The man works in the city\",\n",
+        "    \"The woman lives in the town\"\n",
+        "]\n",
+        "target_words = ['king', 'queen', 'man', 'woman']\n",
+        "\n",
+        "# Load tokenizer and model\n",
+        "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')\n",
+        "model = AutoModel.from_pretrained('bert-base-uncased')\n",
+        "\n",
+        "# Extract embeddings for target words\n",
+        "word_emb_dict = {}\n",
+        "for text in texts:\n",
+        "    inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)\n",
+        "    tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0])\n",
+        "    with torch.no_grad():\n",
+        "        outputs = model(**inputs)\n",
+        "    embeddings = outputs.last_hidden_state[0]\n",
+        "\n",
+        "    for token, emb in zip(tokens, embeddings):\n",
+        "        # We only want the first occurrence of each target word to ensure consistent embedding\n",
+        "        if token in target_words and token not in word_emb_dict:\n",
+        "            word_emb_dict[token] = emb\n",
+        "\n",
+        "# Ensure all target words were found\n",
+        "if len(word_emb_dict) < len(target_words):\n",
+        "    print(f\"Warning: Not all target words were found. Found: {list(word_emb_dict.keys())}\")\n",
+        "    # Handle missing words, e.g., by skipping the analogy or using a placeholder\n",
+        "    # For this example, we'll stop if a key word for the analogy is missing.\n",
+        "    if 'king' not in word_emb_dict or 'man' not in word_emb_dict or \\\n",
+        "       'woman' not in word_emb_dict or 'queen' not in word_emb_dict:\n",
+        "        print(\"Essential words for the analogy are missing. Exiting.\")\n",
+        "        exit()\n",
+        "\n",
+        "\n",
+        "# Prepare vectors for analogy\n",
+        "king_emb = word_emb_dict['king']\n",
+        "man_emb = word_emb_dict['man']\n",
+        "woman_emb = word_emb_dict['woman']\n",
+        "queen_emb = word_emb_dict['queen']\n",
+        "\n",
+        "# Compute analogy vector\n",
+        "analogy_vector = king_emb - man_emb + woman_emb\n",
+        "\n",
+        "# Reduce dimensions using PCA\n",
+        "vectors = torch.stack([king_emb, man_emb, woman_emb, queen_emb, analogy_vector])\n",
+        "labels = ['king', 'man', 'woman', 'queen', 'king - man + woman']\n",
+        "\n",
+        "# Change n_components to 3 for 3D visualization\n",
+        "pca = PCA(n_components=3)\n",
+        "reduced = pca.fit_transform(vectors.detach().numpy()) # Use .detach().numpy() for tensors\n",
+        "\n",
+        "# Plot\n",
+        "fig = plt.figure(figsize=(12, 10)) # Adjusted figure size for 3D and longer labels\n",
+        "ax = fig.add_subplot(111, projection='3d') # Create a 3D subplot\n",
+        "\n",
+        "for i, label_text in enumerate(labels): # Renamed 'label' to 'label_text' to avoid conflict\n",
+        "    x, y, z = reduced[i]\n",
+        "    ax.scatter(x, y, z, s=50, label=label_text if i < 4 else None) # Add actual points to legend for clarity\n",
+        "    \n",
+        "    # Create the text label with coordinates\n",
+        "    # Displaying coordinates rounded to 2 decimal places\n",
+        "    point_label = f\"{label_text}\\n({x:.2f}, {y:.2f}, {z:.2f})\"\n",
+        "    ax.text(x + 0.02, y + 0.02, z + 0.02, point_label, fontsize=9) # Adjusted offset and fontsize\n",
+        "\n",
+        "ax.set_title(\"3D Word Analogy Visualization with Coordinates\")\n",
+        "ax.set_xlabel(\"PCA Component 1\")\n",
+        "ax.set_ylabel(\"PCA Component 2\")\n",
+        "ax.set_zlabel(\"PCA Component 3\")\n",
+        "\n",
+        "# Create a legend for the actual word points (king, queen, man, woman)\n",
+        "# The analogy vector is represented by its text label.\n",
+        "# We can add a specific marker for the analogy result or just rely on its text.\n",
+        "# For simplicity, we'll just use text for all points.\n",
+        "# If you want a legend for the scatter points:\n",
+        "handles, plot_labels = ax.get_legend_handles_labels() # Get existing handles and labels\n",
+        "if handles: # Check if there are any handles to create a legend for\n",
+        "    ax.legend(handles, plot_labels, title=\"Words\")\n",
+        "\n",
+        "plt.grid(True)\n",
+        "plt.tight_layout()\n",
+        "plt.show()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.13.2"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}
diff --git a/lectures/11_sentiment_analysis_embeddings/0_panda_tutorial.ipynb b/lectures/11_sentiment_analysis_embeddings/0_panda_tutorial.ipynb
new file mode 100644
index 0000000..4ab8052
--- /dev/null
+++ b/lectures/11_sentiment_analysis_embeddings/0_panda_tutorial.ipynb
@@ -0,0 +1,1060 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "f25c7795",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>phrase</th>\n",
+       "      <th>sentiment</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>The Matrix is great, revolutionary sci-fi that...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Terrible movie, The Matrix’s plot is so confus...</td>\n",
+       "      <td>negative</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>The Matrix was okay, entertaining but not life...</td>\n",
+       "      <td>neutral</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Great visuals and action in The Matrix make it...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Hated The Matrix; terrible pacing and a story ...</td>\n",
+       "      <td>negative</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id                                             phrase sentiment\n",
+       "0   1  The Matrix is great, revolutionary sci-fi that...  positive\n",
+       "1   2  Terrible movie, The Matrix’s plot is so confus...  negative\n",
+       "2   3  The Matrix was okay, entertaining but not life...   neutral\n",
+       "3   4  Great visuals and action in The Matrix make it...  positive\n",
+       "4   5  Hated The Matrix; terrible pacing and a story ...  negative"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 📌 Step 1: Import pandas\n",
+    "# Pandas is a powerful library for data analysis and manipulation.\n",
+    "import pandas as pd\n",
+    "\n",
+    "# 📌 Step 2: Load the CSV file\n",
+    "# Make sure the CSV file is in the same directory as this notebook.\n",
+    "# If your file has no header row, you can use: pd.read_csv('filename.csv', header=None)\n",
+    "df = pd.read_csv(\"matrix_reviews.csv\")\n",
+    "\n",
+    "# 📌 Step 3: Display the first few rows\n",
+    "# This helps you preview the data and verify that it loaded correctly.\n",
+    "df.head()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "cf32b9de",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>phrase</th>\n",
+       "      <th>sentiment</th>\n",
+       "      <th>phrase_length</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>The Matrix is great, revolutionary sci-fi that...</td>\n",
+       "      <td>positive</td>\n",
+       "      <td>81</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Terrible movie, The Matrix’s plot is so confus...</td>\n",
+       "      <td>negative</td>\n",
+       "      <td>78</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>The Matrix was okay, entertaining but not life...</td>\n",
+       "      <td>neutral</td>\n",
+       "      <td>64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Great visuals and action in The Matrix make it...</td>\n",
+       "      <td>positive</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Hated The Matrix; terrible pacing and a story ...</td>\n",
+       "      <td>negative</td>\n",
+       "      <td>74</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>6</td>\n",
+       "      <td>The Matrix is awesome, with mind-bending conce...</td>\n",
+       "      <td>positive</td>\n",
+       "      <td>77</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>7</td>\n",
+       "      <td>Terrible acting in The Matrix makes it hard to...</td>\n",
+       "      <td>negative</td>\n",
+       "      <td>68</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>8</td>\n",
+       "      <td>Watched The Matrix, it’s decent but overhyped....</td>\n",
+       "      <td>neutral</td>\n",
+       "      <td>52</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>9</td>\n",
+       "      <td>Great story, The Matrix blends philosophy and ...</td>\n",
+       "      <td>positive</td>\n",
+       "      <td>74</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>10</td>\n",
+       "      <td>The Matrix is terrible, too complex and preten...</td>\n",
+       "      <td>negative</td>\n",
+       "      <td>76</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id                                             phrase sentiment  \\\n",
+       "0   1  The Matrix is great, revolutionary sci-fi that...  positive   \n",
+       "1   2  Terrible movie, The Matrix’s plot is so confus...  negative   \n",
+       "2   3  The Matrix was okay, entertaining but not life...   neutral   \n",
+       "3   4  Great visuals and action in The Matrix make it...  positive   \n",
+       "4   5  Hated The Matrix; terrible pacing and a story ...  negative   \n",
+       "5   6  The Matrix is awesome, with mind-bending conce...  positive   \n",
+       "6   7  Terrible acting in The Matrix makes it hard to...  negative   \n",
+       "7   8  Watched The Matrix, it’s decent but overhyped....   neutral   \n",
+       "8   9  Great story, The Matrix blends philosophy and ...  positive   \n",
+       "9  10  The Matrix is terrible, too complex and preten...  negative   \n",
+       "\n",
+       "   phrase_length  \n",
+       "0             81  \n",
+       "1             78  \n",
+       "2             64  \n",
+       "3             75  \n",
+       "4             74  \n",
+       "5             77  \n",
+       "6             68  \n",
+       "7             52  \n",
+       "8             74  \n",
+       "9             76  "
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[:10]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "7495b1df",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "pandas.core.frame.DataFrame"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(df[:10])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "6d9d5eb1",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    The Matrix is great, revolutionary sci-fi that...\n",
+       "1    Terrible movie, The Matrix’s plot is so confus...\n",
+       "2    The Matrix was okay, entertaining but not life...\n",
+       "3    Great visuals and action in The Matrix make it...\n",
+       "4    Hated The Matrix; terrible pacing and a story ...\n",
+       "Name: phrase, dtype: object"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[:5]['phrase']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "1d5fb3da",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    81\n",
+       "1    78\n",
+       "2    64\n",
+       "3    75\n",
+       "4    74\n",
+       "Name: phrase, dtype: int64"
+      ]
+     },
+     "execution_count": 33,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[:5]['phrase'].str.len()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "79546d50",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['The Matrix is great, revolutionary sci-fi that redefined action films! #mindblown',\n",
+       " 'Terrible movie, The Matrix’s plot is so confusing and overrated. #disappointed',\n",
+       " 'The Matrix was okay, entertaining but not life-changing. #movies',\n",
+       " 'Great visuals and action in The Matrix make it a must-watch classic. #scifi',\n",
+       " 'Hated The Matrix; terrible pacing and a story that drags on forever. #fail']"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[:5]['phrase'].tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "0500eaed",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "<class 'pandas.core.frame.DataFrame'>\n",
+      "RangeIndex: 50 entries, 0 to 49\n",
+      "Data columns (total 3 columns):\n",
+      " #   Column     Non-Null Count  Dtype \n",
+      "---  ------     --------------  ----- \n",
+      " 0   id         50 non-null     int64 \n",
+      " 1   phrase     50 non-null     object\n",
+      " 2   sentiment  50 non-null     object\n",
+      "dtypes: int64(1), object(2)\n",
+      "memory usage: 1.3+ KB\n"
+     ]
+    }
+   ],
+   "source": [
+    "# 📌 Step 4: Basic information about the dataset\n",
+    "# Useful for checking column names, data types, and missing values.\n",
+    "df.info()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "19e5db8c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "id           0\n",
+       "phrase       0\n",
+       "sentiment    0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 📌 Step 5: Check for missing values\n",
+    "# It's always good practice to check for missing or null data.\n",
+    "df.isnull().sum()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "a00e0504",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "sentiment\n",
+       "positive    20\n",
+       "negative    20\n",
+       "neutral     10\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 📌 Step 6: Get basic statistics\n",
+    "# For numerical columns, describe() gives count, mean, std, min, etc.\n",
+    "# For categorical data, use value_counts().\n",
+    "df.describe()\n",
+    "df['sentiment'].value_counts()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "cd2e8c90",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0    1\n",
+       "1    0\n",
+       "2    2\n",
+       "3    1\n",
+       "4    0\n",
+       "5    1\n",
+       "6    0\n",
+       "7    2\n",
+       "8    1\n",
+       "9    0\n",
+       "Name: sentiment, dtype: int64"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[:10]['sentiment'].map({'positive': 1, 'negative': 0, 'neutral': 2})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "be78d597",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "pandas.core.series.Series"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "s=df[:10]['sentiment'].map({'positive': 1, 'negative': 0, 'neutral': 2})\n",
+    "type(s)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "b1487b2c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[1, 0, 2, 1, 0, 1, 0, 2, 1, 0]"
+      ]
+     },
+     "execution_count": 32,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "s.tolist()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "5210796b",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkAAAAHHCAYAAABXx+fLAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjEsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvc2/+5QAAAAlwSFlzAAAPYQAAD2EBqD+naQAAb21JREFUeJzt3XlcVGX7P/DPmRnAkVVlS1ERXEANSCVzwSU1TFsoNUN73M36WpGmpW1KWZSUtlny9Dyp9STt2kJZZi6YS1EgmZomoJGSDLEqMsu5f3/448A4M8jgDGDzefvi9fJcc+ac6z73zXDNfc6ckYQQAkREREQuRNXSCRARERE1NxZARERE5HJYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQuhwUQERERuRwWQNTqzZgxA6GhoS2dRotbv349JElCQUGB0/d18TEvKCiAJEl44YUXnL5vAFi+fDkkSWqWfV1MkiQsX7682fdb22adTtfs+24NWrLPHW3EiBEYMWJES6dBl8ACiMz88ssvmDhxIrp27Yo2bdqgU6dOGDNmDF599VWn7vfUqVNYvnw5cnJynLofZzl37hyWL1+OHTt2NGr9HTt2QJIk5cfDwwNBQUEYMWIEnn32WRQXF7dIXs2pNefmCBf3cUM/zam2kJYkCbt377Z4XAiBzp07Q5Ik3HTTTU3ax7PPPovNmzdfZqaXZ8SIEWbHWKvVIioqCi+99BJkWW7R3Kh10LR0AtR67NmzByNHjkSXLl0wd+5cBAcH448//sC+ffvw8ssv4/7773favk+dOoXk5GSEhoYiJibG7LE333yz1b9gnTt3DsnJyQBg1zu/Bx54ALGxsTCZTCguLsaePXuwbNkyrFq1Ch988AGuv/56Zd1//etfuPPOO+Hh4eH0vJrjmDeU2+OPP44lS5Y4df+2VFdXQ6O5/JfGyMhIvPPOO2axpUuXwsvLC4899thlb/9ytWnTBhs3bsTQoUPN4jt37kRhYaFd4+xizz77LCZOnIiEhIRGP8cZfR4SEoKUlBQAgE6nw8aNG7FgwQIUFxfjmWeecei+6vvmm2+ctm1yHBZApHjmmWfg6+uLH3/8EX5+fmaPnTlzpmWSAuDm5tZi+3a2uLg4TJw40Sx24MAB3HDDDZgwYQIOHTqEq666CgCgVquhVqudms/Zs2fh6enZ4sdco9E4pAhpijZt2jhkO0FBQbjrrrvMYs899xz8/f0t4i1h3Lhx+PDDD/HKK6+YHeuNGzeif//+zXYqrnbMOaPPfX19zY71Pffcg4iICLz66qt46qmnnPb75O7u7pTtkmPxFBgpjh8/jj59+lgUPwAQGBhoEfvf//6H/v37Q6vVon379rjzzjvxxx9/mK0zYsQI9O3bF4cOHcLIkSPRtm1bdOrUCStXrlTW2bFjB2JjYwEAM2fOVKas169fD6Dh61HWrFmDsLAwtG3bFjfccAP++OMPCCHw9NNPIyQkBFqtFrfeeiv+/vtvi/y/+uorxMXFwdPTE97e3hg/fjx+/fVXs3VmzJgBLy8v/Pnnn0hISICXlxcCAgKwaNEimEwmJZ+AgAAAQHJyspJ/U68jiY6OxksvvYSysjK89tprStzaNUBZWVmIj4+Hv78/tFotunXrhlmzZjUqr9q2HT9+HOPGjYO3tzemTp1q9ZjXt3r1anTt2hVarRbDhw/HwYMHzR63df1D/W1eKjdr14MYjUY8/fTTCA8Ph4eHB0JDQ/Hoo4+ipqbGbL3Q0FDcdNNN2L17N6699lq0adMGYWFhePvtt60f8Itc3He1ufz++++YMWMG/Pz84Ovri5kzZ+LcuXON2qY9ysrKGrWfxvz+NSQxMRElJSXYunWrEtPr9fjoo48wZcoUq8954YUXMHjwYHTo0AFarRb9+/fHRx99ZLaOJEk4e/YsNmzYoPTrjBkzANQdy0OHDmHKlClo166dMgN1cZ+vW7cOkiThrbfeMtv+s88+C0mS8OWXXza6rbXatGmD2NhYVFZWWrypu9TxvO++++Dl5WW1LxITExEcHKy8Jlj7HaipqcGyZcvQvXt3eHh4oHPnznj44YfNxu/tt9+Ofv36mT3v5ptvhiRJ+Oyzz5TY/v37IUkSvvrqKwCAwWBAcnIyevTogTZt2qBDhw4YOnSoWd+SJRZApOjatSt++ukniz9o1jzzzDOYNm0aevTogVWrVuHBBx/Etm3bMGzYMJSVlZmtW1pairFjxyI6OhovvvgiIiIi8Mgjjyi/vJGRkXjqqacAAHfffTfeeecdvPPOOxg2bFiDObz77rt4/fXXcf/99+Ohhx7Czp07cccdd+Dxxx/Hli1b8Mgjj+Duu+/G559/jkWLFpk995133sH48ePh5eWF559/Hk888QQOHTqEoUOHWlxkbDKZEB8fjw4dOuCFF17A8OHD8eKLL+Lf//43ACAgIABvvPEGAOC2225T8r/99tsveRxtmThxIrRabYNT6WfOnMENN9yAgoICLFmyBK+++iqmTp2Kffv2NTovo9GI+Ph4BAYG4oUXXsCECRMazOvtt9/GK6+8gvnz52Pp0qU4ePAgrr/+evz11192ta8px2zOnDl48skn0a9fP6xevRrDhw9HSkoK7rzzTot1f//9d0ycOBFjxozBiy++iHbt2mHGjBkWBa497rjjDlRWViIlJQV33HEH1q9fr5zCc6TG7Mee3z9bQkNDMWjQIKSnpyuxr776CuXl5VaPKQC8/PLLuOaaa/DUU0/h2WefhUajwaRJk5CRkaGs884778DDwwNxcXFKv86bN89sO5MmTcK5c+fw7LPPYu7cuVb3NXPmTNx0001YuHChUoj88ssvSE5OxuzZszFu3LhGtfNitW+g6r/Ra8zxnDx5Ms6ePWvWVuDCqdzPP/8cEydOtDmjJMsybrnlFrzwwgu4+eab8eqrryIhIQGrV6/G5MmTlfXi4uJw4MABVFRUALhwPdb3338PlUqFzMxMZb3MzEyoVCoMGTIEwIXiMTk5GSNHjsRrr72Gxx57DF26dMHPP//cpGPkMgTR//fNN98ItVot1Gq1GDRokHj44YfF119/LfR6vdl6BQUFQq1Wi2eeecYs/ssvvwiNRmMWHz58uAAg3n77bSVWU1MjgoODxYQJE5TYjz/+KACIdevWWeQ1ffp00bVrV2U5Pz9fABABAQGirKxMiS9dulQAENHR0cJgMCjxxMRE4e7uLs6fPy+EEKKyslL4+fmJuXPnmu2nqKhI+Pr6msWnT58uAIinnnrKbN1rrrlG9O/fX1kuLi4WAMSyZcss8rdm+/btAoD48MMPba4THR0t2rVrpyyvW7dOABD5+flCCCE2bdokAIgff/zR5jYayqu2bUuWLLH6mLVjrtVqRWFhoRLfv3+/ACAWLFigxIYPHy6GDx9+yW02lNuyZctE/ZennJwcAUDMmTPHbL1FixYJAOK7775TYl27dhUAxK5du5TYmTNnhIeHh3jooYcs9nWxi3OqzWXWrFlm6912222iQ4cOl9xefX369LF6bOzZjz2/f9bUjqMff/xRvPbaa8Lb21ucO3dOCCHEpEmTxMiRI4UQF47j+PHjzZ5bu14tvV4v+vbtK66//nqzuKenp5g+fbrNNiYmJtp8rL7Tp0+L9u3bizFjxoiamhpxzTXXiC5duojy8vIG2yjEhXEYEREhiouLRXFxsThy5IhYvHixAGDWrsYeT1mWRadOncxet4QQ4oMPPrAYbxf/DrzzzjtCpVKJzMxMs+euXbtWABDff/+9EKLudfDLL78UQgiRm5srAIhJkyaJgQMHKs+75ZZbxDXXXKMsR0dHW/QVXRpngEgxZswY7N27F7fccgsOHDiAlStXIj4+Hp06dTKbfv3kk08gyzLuuOMO6HQ65Sc4OBg9evTA9u3bzbbr5eVldh7e3d0d1157LfLy8i4r30mTJsHX11dZHjhwIADgrrvuMruWYODAgdDr9fjzzz8BAFu3bkVZWRkSExPN8ler1Rg4cKBF/sCFawfqi4uLu+z8L8XLywuVlZU2H699B/vFF1/AYDA0eT/33ntvo9dNSEhAp06dlOVrr70WAwcObNLpCHvUbn/hwoVm8YceeggALN6V9+7dG3FxccpyQEAAevXqdVl9Zm0MlJSUKO/WHeVS+7H3968hd9xxB6qrq/HFF1+gsrISX3zxhc3TXwCg1WqV/5eWlqK8vBxxcXF2zzRc3EZbgoODsWbNGmzduhVxcXHIycnBW2+9BR8fn0Y9/8iRIwgICEBAQAAiIiKQmpqKW265RTm9DjT+eEqShEmTJuHLL79EVVWV8vz3338fnTp1sriYvL4PP/wQkZGRiIiIMNtH7YccavdxzTXXwMvLC7t27QJwYaYnJCQE06ZNw88//4xz585BCIHdu3ebjW8/Pz/8+uuvOHbsWKOOC13Ai6DJTGxsLD755BPo9XocOHAAmzZtwurVqzFx4kTk5OSgd+/eOHbsGIQQ6NGjh9VtXHwBbUhIiMX1HO3atUNubu5l5dqlSxez5dpiqHPnzlbjpaWlAKC8SNT/hFV9F7+4tmnTRrlepVa7du2U7TlLVVUVvL29bT4+fPhwTJgwAcnJyVi9ejVGjBiBhIQETJkypdGf4NFoNAgJCWl0Ttb6vGfPnvjggw8avY2mOHHiBFQqFbp3724WDw4Ohp+fH06cOGEWv3hsAJffZxdvs127dgAujKvG/kF2xH7s/f1rSEBAAEaPHo2NGzfi3LlzMJlMFhfl1/fFF19gxYoVyMnJMbt2xd6P8nfr1q3R695555343//+h4yMDNx9990YNWpUo58bGhqqfKLx+PHjeOaZZ1BcXGx2obs9x3Py5Ml46aWX8Nlnn2HKlCmoqqrCl19+iXnz5jV4DI4dO4bDhw9bvI7Uqr0eSa1WY9CgQcrprszMTMTFxWHo0KEwmUzYt28fgoKC8Pfff5sVQE899RRuvfVW9OzZE3379sXYsWPxr3/9C1FRUY0+Vq6IBRBZ5e7ujtjYWMTGxqJnz56YOXMmPvzwQyxbtgyyLCsX4Fk75+3l5WW2bOu8uBDisnK0td1L7a/2493vvPMOgoODLda7+JMozv7klTUGgwFHjx5F3759ba4jSRI++ugj7Nu3D59//jm+/vprzJo1Cy+++CL27dtn0Q/WeHh4QKVy7ESwJElW+7b2AtHL3XZjOGPMOWsc27sfe3//LmXKlCmYO3cuioqKcOONN1r9EARw4Y/xLbfcgmHDhuH111/HVVddBTc3N6xbtw4bN260a5/1Z5IupaSkBFlZWQCAQ4cOQZblRo9ZT09PjB49WlkeMmQI+vXrh0cffRSvvPIKAPuO53XXXYfQ0FB88MEHmDJlCj7//HNUV1ebXcdjjSzLuPrqq7Fq1Sqrj9d/0zZ06FA888wzOH/+PDIzM/HYY4/Bz88Pffv2RWZmJoKCggDArAAaNmwYjh8/jk8//RTffPMN/vOf/2D16tVYu3Yt5syZ04gj5ZpYANElDRgwAABw+vRpAEB4eDiEEOjWrRt69uzpkH00583gwsPDAVz4ZFv9F8fL4ej8P/roI1RXVyM+Pv6S61533XW47rrr8Mwzz2Djxo2YOnUq3nvvPcyZM8fheVmbYj969KjZJ8batWtn9VTTxbM09uTWtWtXyLKMY8eOITIyUon/9ddfKCsrQ9euXRu9rSudo3//brvtNsybNw/79u3D+++/b3O9jz/+GG3atMHXX39tNsO4bt06i3UdOe7mz5+vXBS+dOlSvPTSSxanQhsrKioKd911F9LS0rBo0SJ06dLF7uN5xx134OWXX0ZFRQXef/99hIaG4rrrrmvwOeHh4Thw4ABGjRp1yWMTFxcHvV6P9PR0/Pnnn0qhM2zYMKUA6tmzp1II1Wrfvj1mzpyJmTNnoqqqCsOGDcPy5ctZADWA1wCRYvv27VbfzdZef9GrVy8AFz6qqVarkZycbLG+EAIlJSV279vT0xMAGv0JlssRHx8PHx8fPPvss1avnWnKXZjbtm0LwDH5HzhwAA8++CDatWuH+fPn21yvtLTU4vjX3kSy9vSEI/MCgM2bNyvXUgHADz/8gP379+PGG29UYuHh4Thy5IjZcTxw4AC+//57s23Zk1vtJ35eeukls3jtO+rx48fb1Y4rmaN//7y8vPDGG29g+fLluPnmm22up1arIUmS2UxeQUGB1Ts+e3p6OmTMffTRR3j//ffx3HPPYcmSJbjzzjvx+OOP4+jRo03e5sMPPwyDwaCMHXuP5+TJk1FTU4MNGzZgy5YtuOOOOy65zzvuuAN//vkn3nzzTYvHqqurcfbsWWV54MCBcHNzw/PPP4/27dujT58+AC4URvv27cPOnTvNZn8AWOTo5eWF7t27W9wigsxxBogU999/P86dO4fbbrsNERER0Ov12LNnj/IuZ+bMmQAu/IFbsWIFli5dioKCAiQkJMDb2xv5+fnYtGkT7r77bouPnV9KeHg4/Pz8sHbtWnh7e8PT0xMDBw6061qBxvLx8cEbb7yBf/3rX+jXrx/uvPNOBAQE4OTJk8jIyMCQIUPM7r/TGFqtFr1798b777+Pnj17on379ujbt2+Dp7CAC6cVzp8/D5PJhJKSEnz//ff47LPP4Ovri02bNlk9RVdrw4YNeP3113HbbbchPDwclZWVePPNN+Hj46MUDE3Ny5bu3btj6NChuPfee1FTU4OXXnoJHTp0wMMPP6ysM2vWLKxatQrx8fGYPXs2zpw5g7Vr16JPnz5mFwzbk1t0dDSmT5+Of//73ygrK8Pw4cPxww8/YMOGDUhISMDIkSOb1J4rkTN+/6ZPn37JdcaPH49Vq1Zh7NixmDJlCs6cOYM1a9age/fuFtfz9e/fH99++y1WrVqFjh07olu3bsqHFBrrzJkzuPfeezFy5Ejcd999AIDXXnsN27dvx4wZM7B79+4mnb7t3bs3xo0bh//85z944okn7D6e/fr1Q/fu3fHYY4+hpqbmkqe/gAt3cf/ggw9wzz33YPv27RgyZAhMJhOOHDmCDz74AF9//bUy0962bVv0798f+/btU+4BBFyYATp79izOnj1rUQD17t0bI0aMQP/+/dG+fXtkZWXho48+Uo4b2dCsnzmjVu2rr74Ss2bNEhEREcLLy0u4u7uL7t27i/vvv1/89ddfFut//PHHYujQocLT01N4enqKiIgIMX/+fPHbb78p6wwfPlz06dPH4rkXfyRaCCE+/fRT0bt3b6HRaMw+Em/rI9mpqalmz7f10fL6H/u9eP34+Hjh6+sr2rRpI8LDw8WMGTNEVlaWWZ6enp4W+Vv7yO6ePXtE//79hbu7+yU/El+ba+2Pm5ubCAgIEMOGDRPPPPOMOHPmjMVzLv4Y/M8//ywSExNFly5dhIeHhwgMDBQ33XSTWf4N5WWrbbWP2TrmL774oujcubPw8PAQcXFx4sCBAxbP/9///ifCwsKEu7u7iImJEV9//bXVPreVm7XjazAYRHJysujWrZtwc3MTnTt3FkuXLlVub1DL2se3hbD98fyLXdx3tbkUFxebrXdxfzRGYz4G39j9NOb3zxpbvw8Xs3Yc//vf/4oePXoIDw8PERERIdatW2e1r44cOSKGDRsmtFqtAKB8JN5WG+s/Vuv2228X3t7eoqCgwGy9Tz/9VAAQzz//fIP523rtEUKIHTt2WPSzPcfzscceEwBE9+7dbe774n7W6/Xi+eefF3369BEeHh6iXbt2on///iI5OdniY/21H9e/uI3du3cXAMTx48fN4itWrBDXXnut8PPzE1qtVkRERIhnnnnG4hYmZE4SwsFX8BERERG1crwGiIiIiFwOCyAiIiJyOSyAiIiIyOWwACIiIiKXwwKIiIiIXA4LICIiInI5vBGiFbIs49SpU/D29m7Wr2ggIiKiphNCoLKyEh07drzkjTJZAFlx6tQpi28UJyIioivDH3/8gZCQkAbXYQFkhbe3N4ALB9DHx6eFsyEiIqLGqKioQOfOnZW/4w1hAWRF7WkvHx8fFkBERERXmMZcvsKLoImIiMjlsAAiIiIil8MCiIiIiFwOCyAiIiJyOSyAiIiIyOWwACIiIiKXwwKIiIiIXA4LICIiInI5LICIiIjI5bAAIiIiIpfTogVQSkoKYmNj4e3tjcDAQCQkJOC3334zW+f8+fOYP38+OnToAC8vL0yYMAF//fVXg9sVQuDJJ5/EVVddBa1Wi9GjR+PYsWPObAoRERFdQVq0ANq5cyfmz5+Pffv2YevWrTAYDLjhhhtw9uxZZZ0FCxbg888/x4cffoidO3fi1KlTuP322xvc7sqVK/HKK69g7dq12L9/Pzw9PREfH4/z5887u0lERER0BZCEEKKlk6hVXFyMwMBA7Ny5E8OGDUN5eTkCAgKwceNGTJw4EQBw5MgRREZGYu/evbjuuusstiGEQMeOHfHQQw9h0aJFAIDy8nIEBQVh/fr1uPPOOy+ZR0VFBXx9fVFeXs4vQyUiIrpC2PP3u1VdA1ReXg4AaN++PQDgp59+gsFgwOjRo5V1IiIi0KVLF+zdu9fqNvLz81FUVGT2HF9fXwwcONDmc4iIiMi1aFo6gVqyLOPBBx/EkCFD0LdvXwBAUVER3N3d4efnZ7ZuUFAQioqKrG6nNh4UFNTo59TU1KCmpkZZrqioAAAYjUYYjUYAgEqlgkqlgizLkGVZWbc2bjKZUH8yzVZcrVZDkiRlu/XjAGAymRoV12g0EEKYxSVJglqttsjRVpxtYpvYJraJbWKb/mltaqxWUwDNnz8fBw8exO7du5t93ykpKUhOTraIZ2dnw9PTEwAQEBCA8PBw5Ofno7i4WFknJCQEISEhOHr0qDKDBQBhYWEIDAzEwYMHUV1drcQjIiLg5+eH7Oxss46KioqCu7s7srKyzHIYMGAA9Ho9cnNzlZharUZsbCy6p3ZHYnCiEtcZdEgrTEOMdwzG+49X4nnVeUgvSscwv2GIaxenxHMqc5Chy8B4//GI8Y5R4pmlmdhVtguJwYkI04Yp8QxdBnIqczAvZB783fyVeHpROvKq87C462K4q9yVeFphGiqMFVgcutisTakFqfDR+GBeyDwlppf1SD2RijBtWIu0KSchx2n9VF5ejiNHjihxrVaL6Oho6HQ65OXlKXFfX19ERkbi1KlTKCwsVOKtcew12KZXXqlrU14eItPTcWrYMBTG1fVTQE4OwjMykD9+PIpjYuralJmJkF27cDQxEeVhdf0UlpGBwJwcHJw3D9X+dWMvIj0dfnl5yF68GCb3urEXlZYG94oKZC02H3sDUlOh9/FB7ry6safW6xGbmorysDAcSawbe1qdDtFpadDFxCBvfN3Ya7Y2/fADxx7bxDbZ2aZDhw6hsVrFNUD33XcfPv30U+zatQvdunVT4t999x1GjRqF0tJSs1mgrl274sEHH8SCBQsstpWXl4fw8HBkZ2cjpt6L0PDhwxETE4OXX37Z4jnWZoA6d+6MkpIS5Rxia6yw1clqaKS6GlZAwCAMUEFlNa6GGmpJrcRlyDAKIzSSBqp6Z0NNwgQTTHCT3CBBUuJGYYQM2WbcXar7AwQABmGAgLCI64UeEiS4SW4WcVu5O7tNxseN/8h3Qi3SJq22Li4E1AYDZLUasrqun1SyDJXRCFmjgayq6yeVyQSVyQSTmxuEVNdPKqMRKlm2iKuNRkiyDKO7+RhTGwyAEGZFEXCh2IEkweRmPvY0ej2ESgWTpm6MKbmrVJCtxZ3dJoPBPHeOPbaJbbpkm0pLS9G+fftGXQPUojNAQgjcf//92LRpE3bs2GFW/ABA//794ebmhm3btmHChAkAgN9++w0nT57EoEGDrG6zW7duCA4OxrZt25QCqKKiAvv378e9995r9TkeHh7w8PCwiGs0Gmg05oeo9iBfTF3vhbAx8Yu325S4DBl6oW903AQTTMJyetAojBYx4EIBY0/c2j5txQWEXbk7u03O7CdJkqzGbY0le+MtMfYabJPesp9qiwCLuNFo9UJEtcFGP9mIa6zs02ZcCKtxSZatxlWy3DJt4thjm9gmh7XJmha9CHr+/Pn43//+h40bN8Lb2xtFRUUoKipSpuR8fX0xe/ZsLFy4ENu3b8dPP/2EmTNnYtCgQWafAIuIiMCmTZsAXDjoDz74IFasWIHPPvsMv/zyC6ZNm4aOHTsiISGhJZpJRERErUyLzgC98cYbAIARI0aYxdetW4cZM2YAAFavXg2VSoUJEyagpqYG8fHxeP31183W/+2338zOBT788MM4e/Ys7r77bpSVlWHo0KHYsmUL2rRp49T2EBER0ZWhVVwD1NpcKfcBkpKlS69EjSKW8dfAYSSOS4fgSzOR3a7Y+wARERERNQcWQERERORyWAARERGRy2EBRERERC6HBRARERG5HBZARERE5HJYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQuhwUQERERuRwWQERERORyWAARERGRy2EBRERERC6HBRARERG5HBZARERE5HJYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQuhwUQERERuRwWQERERORyWAARERGRy2EBRERERC6HBRARERG5HBZARERE5HJYABEREZHLYQFERERELocFEBEREbmcFi2Adu3ahZtvvhkdO3aEJEnYvHmz2eOSJFn9SU1NtbnN5cuXW6wfERHh5JYQERHRlaRFC6CzZ88iOjoaa9assfr46dOnzX7eeustSJKECRMmNLjdPn36mD1v9+7dzkifiIiIrlCaltz5jTfeiBtvvNHm48HBwWbLn376KUaOHImwsLAGt6vRaCyeS0RERFTrirkG6K+//kJGRgZmz559yXWPHTuGjh07IiwsDFOnTsXJkyebIUMiIiK6UrToDJA9NmzYAG9vb9x+++0Nrjdw4ECsX78evXr1wunTp5GcnIy4uDgcPHgQ3t7eVp9TU1ODmpoaZbmiogIAYDQaYTQaAQAqlQoqlQqyLEOWZWXd2rjJZIIQ4pJxtVoNSZKU7daPA4DJZGpUXKPRQAUVNFJdFwoIGITBZlwNNdSSWonLkGEURmikC9uqZRImmGCCm+QGCZISNwojZMg24+6Su1mOBmGAgLCI64UeEiS4SW4W8ZZqkzP7SQhhFpckCWq12mIs2Yq3xrHXYJvc6/pbEgJqgwGyWg1ZXddPKlmGymiErNFAVtX1k8pkgspkgsnNDUKq6yeV0QiVLFvE1UYjJFmG0d18jKkNBkAImC6O6/WAJMHkZj72NHo9hEoFk6ZujCm5q1SQrcWd3SaOPbaJbWpSmxrriimA3nrrLUydOhVt2rRpcL36p9SioqIwcOBAdO3aFR988IHN2aOUlBQkJydbxLOzs+Hp6QkACAgIQHh4OPLz81FcXKysExISgpCQEBw9ehTl5eVKPCwsDIGBgTh48CCqq6uVeEREBPz8/JCdnW3WUVFRUXB3d0dWVpZZDgMGDIBer0dubq4SU6vViI2NRag2FInBiUpcZ9AhrTANUd5RGO8/XonnVechvSgdQ/yGIK5dnBLPqcxBhi4D8R3iEeMdo8QzSzOxq2wXJgZNRJi27nRjhi4DOZU5mNVpFvzd/JV4elE68qrzkNQlCe6quj84aYVpqDBWYHHoYrM2pRakwkfjg3kh85SYXtYj9URqi7XJmf1UXl6OI0eOKHGtVovo6GjodDrk5eUpcV9fX0RGRuLUqVMoLCxU4q1x7DXYpsV1/e2bl4fI9HScGjIEhXF1/RSQk4PwjAzkx8ejOCamrk2ZmQjZtQtHJ05Eeb1T3WEZGQjMycHBWbNQ7V839iLS0+GXl4fspCSzYicqLQ3uFRXIWmw+9gakpkLv44PceXVjT63XIzY1FeWhoTiSWDf2tDodotPSoIuKQt74urHXbG3i2GOb2Ca723To0CE0liTql1AtSJIkbNq0CQkJCRaPZWZmYtiwYcjJyUF0dLTd246NjcXo0aORkpJi9XFrM0CdO3dGSUkJfHx8ALTOCludrOYMkIPaZHzc+I98J9QibdJq6+KcAWp6mwwG89w59tgmtumSbSotLUX79u1RXl6u/P225YqYAfrvf/+L/v37N6n4qaqqwvHjx/Gvf/3L5joeHh7w8PCwiGs0Gmg05oeo9iBfTF3vhbAx8Yu325S4DBl6oW903AQTTMJyetAojBYx4EIBY0/c2j5txQWEXbk7u03O7CdJkqzGbY0le+MtMfYabJPesp9qiwCLuNFo9UJEtcFGP9mIa6zs02ZcCKtxSZatxlWy3DJt4thjm9gmh7XJmha9CLqqqgo5OTnIyckBAOTn5yMnJ8fsouWKigp8+OGHmDNnjtVtjBo1Cq+99pqyvGjRIuzcuRMFBQXYs2cPbrvtNqjVaiTWm9omIiIi19aiM0BZWVkYOXKksrxw4UIAwPTp07F+/XoAwHvvvQchhM0C5vjx49DpdMpyYWEhEhMTUVJSgoCAAAwdOhT79u1DQECA8xpCREREV5RWcw1Qa1JRUQFfX99GnUNsSVKydOmVqFHEMv4aOIzEcekQfGkmsps9f7+vmPsAERERETkKCyAiIiJyOSyAiIiIyOWwACIiIiKXwwKIiIiIXA4LICIiInI5LICIiIjI5bAAIiIiIpfDAoiIiIhcDgsgIiIicjksgIiIiMjlsAAiIiIil8MCiIiIiFwOCyAiIiJyOSyAiIiIyOWwACIiIiKXwwKIiIiIXA4LICIiInI5LICIiIjI5bAAIiIiIpfDAoiIiIhcDgsgIiIicjksgIiIiMjlsAAiIiIil8MCiIiIiFwOCyAiIiJyOSyAiIiIyOWwACIiIiKXwwKIiIiIXA4LICIiInI5LICIiIjI5bAAIiIiIpfDAoiIiIhcTosWQLt27cLNN9+Mjh07QpIkbN682ezxGTNmQJIks5+xY8decrtr1qxBaGgo2rRpg4EDB+KHH35wUguIiIjoStSiBdDZs2cRHR2NNWvW2Fxn7NixOH36tPKTnp7e4Dbff/99LFy4EMuWLcPPP/+M6OhoxMfH48yZM45On4iIiK5Qmpbc+Y033ogbb7yxwXU8PDwQHBzc6G2uWrUKc+fOxcyZMwEAa9euRUZGBt566y0sWbLksvIlIiKif4ZWfw3Qjh07EBgYiF69euHee+9FSUmJzXX1ej1++uknjB49WompVCqMHj0ae/fubY50iYiI6ArQojNAlzJ27Fjcfvvt6NatG44fP45HH30UN954I/bu3Qu1Wm2xvk6ng8lkQlBQkFk8KCgIR44csbmfmpoa1NTUKMsVFRUAAKPRCKPRCOBCIaVSqSDLMmRZVtatjZtMJgghLhlXq9WQJEnZbv04AJhMpkbFNRoNVFBBI9V1oYCAQRhsxtVQQy3VHTcZMozCCI10YVu1TMIEE0xwk9wgQVLiRmGEDNlm3F1yN8vRIAwQEBZxvdBDggQ3yc0i3lJtcmY/CSHM4pIkQa1WW4wlW/HWOPYabJN7XX9LQkBtMEBWqyHX+51VyTJURiNkjQayqq6fVCYTVCYTTG5uEFJdP6mMRqhk2SKuNhohyTKM7uZjTG0wAELAdHFcrwckCSY387Gn0eshVCqYNHVjTMldpYJsLe7sNnHssU1sU5Pa1FitugC68847lf9fffXViIqKQnh4OHbs2IFRo0Y5bD8pKSlITk62iGdnZ8PT0xMAEBAQgPDwcOTn56O4uFhZJyQkBCEhITh69CjKy8uVeFhYGAIDA3Hw4EFUV1cr8YiICPj5+SE7O9uso6KiouDu7o6srCyzHAYMGAC9Xo/c3FwlplarERsbi1BtKBKDE5W4zqBDWmEaoryjMN5/vBLPq85DelE6hvgNQVy7OCWeU5mDDF0G4jvEI8Y7RolnlmZiV9kuTAyaiDBtmBLP0GUgpzIHszrNgr+bvxJPL0pHXnUekrokwV1V9wcnrTANFcYKLA5dbNam1IJU+Gh8MC9knhLTy3qknkhtsTY5s5/Ky8vNCnCtVovo6GjodDrk5eUpcV9fX0RGRuLUqVMoLCxU4q1x7DXYpsV1/e2bl4fI9HScGjIEhXF1/RSQk4PwjAzkx8ejOCamrk2ZmQjZtQtHJ05EeVhdP4VlZCAwJwcHZ81CtX/d2ItIT4dfXh6yk5LMip2otDS4V1Qga7H52BuQmgq9jw9y59WNPbVej9jUVJSHhuJIYt3Y0+p0iE5Lgy4qCnnj68Zes7WJY49tYpvsbtOhQ4fQWJKoX0K1IEmSsGnTJiQkJDS4XkBAAFasWIF59V7Aaun1erRt2xYfffSR2XamT5+OsrIyfPrpp1a3aW0GqHPnzigpKYGPjw+A1llhq5PVnAFyUJuMjxv/ke+EWqRNWm1dnDNATW+TwWCeO8ce28Q2XbJNpaWlaN++PcrLy5W/37a06hmgixUWFqKkpARXXXWV1cfd3d3Rv39/bNu2TSmAZFnGtm3bcN9999ncroeHBzw8PCziGo0GGo35Iao9yBezdkquofjF221KXIYMvdA3Om6CCSZhOT1oFEaLGHChgLEnbm2ftuICwq7cnd0mZ/aTJElW47bGkr3xlhh7DbZJb9lPtUWARdxotHohotpgo59sxDVW9mkzLoTVuCTLVuMqWW6ZNnHssU1sk8PaZE2LXgRdVVWFnJwc5OTkAADy8/ORk5ODkydPoqqqCosXL8a+fftQUFCAbdu24dZbb0X37t0RHx+vbGPUqFF47bXXlOWFCxfizTffxIYNG3D48GHce++9OHv2rPKpMCIiIqIWnQHKysrCyJEjleWFCxcCuHDK6o033kBubi42bNiAsrIydOzYETfccAOefvpps9ma48ePQ6fTKcuTJ09GcXExnnzySRQVFSEmJgZbtmyxuDCaiIiIXFeruQaoNamoqICvr2+jziG2JClZuvRK1ChiGX8NHEbiuHQIvjQT2c2ev9+t/j5ARERERI7GAoiIiIhcDgsgIiIicjksgIiIiMjlsAAiIiIil8MCiIiIiFwOCyAiIiJyOXYXQBs2bEBGRoay/PDDD8PPzw+DBw/GiRMnHJocERERkTPYXQA9++yz0P7/Lzvcu3cv1qxZg5UrV8Lf3x8LFixweIJEREREjmb3V2H88ccf6N69OwBg8+bNmDBhAu6++24MGTIEI0aMcHR+RERERA5n9wyQl5cXSkpKAADffPMNxowZAwBo06YNqqurHZsdERERkRPYPQM0ZswYzJkzB9dccw2OHj2KcePGAQB+/fVXhIaGOjo/IiIiIoezewZozZo1GDRoEIqLi/Hxxx+jQ4cOAICffvoJiYmJDk+QiIiIyNH4bfBW8NvgXQ+/Dd6B+G3wjsGXZiK72fP32+5TYMOGDcPIkSMxfPhwDB48GG3atGlyokREREQtwe5TYDfccAP27t2LW265BX5+fhg6dCgef/xxbN26FefOnXNGjkREREQOZfcM0OOPPw4AMBqN+PHHH7Fz507s2LEDK1euhEqlwvnz5x2eJBEREZEj2V0A1crLy8Mvv/yCAwcOIDc3F97e3hg2bJgjcyMiIiJyCrsLoClTpmDnzp2oqanBsGHDMHz4cCxZsgRRUVGQePEjERERXQHsLoDee+89+Pv7Y86cObj++usxdOhQtG3b1hm5ERERETmF3RdBl5SU4D//+Q/0ej2WLl0Kf39/DB48GI8++ii++eYbZ+RIRERE5FCXfR+g33//HStWrMC7774LWZZhMpkclVuL4X2AXA/vA+RAPBXuGLwPEJHdnHofoJKSEuWTXzt27MChQ4fg5+eHm2++GcOHD29y0kRERETNxe4CKDAwEP7+/oiLi8PcuXMxYsQIXH311c7IjYiIiMgp7C6AcnNz0adPH2fkQkRERNQs7L4Iuk+fPjAajfj222+RlpaGyspKAMCpU6dQVVXl8ASJiIiIHM3uGaATJ05g7NixOHnyJGpqajBmzBh4e3vj+eefR01NDdauXeuMPImIiIgcxu4ZoKSkJAwYMAClpaXQarVK/LbbbsO2bdscmhwRERGRM9g9A5SZmYk9e/bA3d3dLB4aGoo///zTYYkREREROYvdM0C27vVTWFgIb29vhyRFRERE5Ex2F0A33HADXnrpJWVZkiRUVVVh2bJlGDdunCNzIyIiInIKu0+Bvfjii4iPj0fv3r1x/vx5TJkyBceOHYO/vz/S09OdkSMRERGRQ9ldAIWEhODAgQN47733kJubi6qqKsyePRtTp041uyiaiIiIqLWy+xQYAGg0Gtx1111YuXIlXn/9dcyZM6dJxc+uXbtw8803o2PHjpAkCZs3b1YeMxgMeOSRR3D11VfD09MTHTt2xLRp03Dq1KkGt7l8+XJIkmT2ExERYXduRERE9M/VqBmgzz77DDfeeCPc3Nzw2WefNbjuLbfc0uidnz17FtHR0Zg1axZuv/12s8fOnTuHn3/+GU888QSio6NRWlqKpKQk3HLLLcjKympwu3369MG3336rLGs0dk90ERER0T9YoyqDhIQEFBUVITAwEAkJCTbXkyTJrm+Dv/HGG3HjjTdafczX1xdbt241i7322mu49tprcfLkSXTp0sXmdjUaDYKDgxudBxEREbmWRp0Ck2UZgYGByv9t/dhT/DRFeXk5JEmCn59fg+sdO3YMHTt2RFhYGKZOnYqTJ086NS8iIiK6sth9buiPP/5A586dnZFLg86fP49HHnkEiYmJ8PHxsbnewIEDsX79evTq1QunT59GcnIy4uLicPDgQZv3KaqpqUFNTY2yXFFRAQAwGo0wGo0AAJVKBZVKpRR7tWrjJpMJQohLxtVqNSRJUrZbPw7Aooi0FddoNFBBBY1U14UCAgZhsBlXQw21pFbiMmQYhREa6cK2apmECSaY4Ca5QYKkxI3CCBmyzbi7ZH5zTIMwQEBYxPVCDwkS3CQ3i3hLtcmZ/SSEMItLkgS1Wm0xlmzFW+PYa7BN9W6SKgkBtcEAWa2GrK7rJ5UsQ2U0QtZoIKvq+kllMkFlMsHk5gYh1fWTymiESpYt4mqjEZIsw3jRjVnVBgMgBEwXx/V6QJJgcjMfexq9HkKlgqne6XIld5UKsrW4s9vEscc2sU1NalNj2V0AhYaGYujQobjrrrswceJEtGvXzt5N2M1gMOCOO+6AEAJvvPFGg+vWP6UWFRWFgQMHomvXrvjggw8we/Zsq89JSUlBcnKyRTw7Oxuenp4AgICAAISHhyM/Px/FxcXKOiEhIQgJCcHRo0dRXl6uxMPCwhAYGIiDBw+iurpaiUdERMDPzw/Z2dlmHRUVFQV3d3eL65sGDBgAvV6P3NxcJaZWqxEbG4tQbSgSgxOVuM6gQ1phGqK8ozDef7wSz6vOQ3pROob4DUFcuzglnlOZgwxdBuI7xCPGO0aJZ5ZmYlfZLkwMmogwbZgSz9BlIKcyB7M6zYK/m78STy9KR151HpK6JMFdVfcHJ60wDRXGCiwOXWzWptSCVPhofDAvZJ4S08t6pJ5IbbE2ObOfysvLceTIESWu1WoRHR0NnU6HvLw8Je7r64vIyEicOnUKhYWFSrw1jr0G27S4rr998/IQmZ6OU0OGoDCurp8CcnIQnpGB/Ph4FMfE1LUpMxMhu3bh6MSJKA+r66ewjAwE5uTg4KxZqPavG3sR6enwy8tDdlKSWbETlZYG94oKZC02H3sDUlOh9/FB7ry6safW6xGbmory0FAcSawbe1qdDtFpadBFRSFvfN3Ya7Y2ceyxTWyT3W06dOgQGksS9UuoRsjOzsbGjRvx3nvvobi4GGPHjsVdd92Fm2++GR4eHvZsyjwRScKmTZssrjGqLX7y8vLw3XffoUOHDnZvOzY2FqNHj0ZKSorVx63NAHXu3BklJSXKbFNrrLDVyWrOADmoTcbHjf/Id0It0qZ6nwjlDNBltMlgMM+dY49tYpsu2abS0lK0b98e5eXlDZ4tAppQANUSQmDHjh3YuHEjPv74Y8iyjNtvvx1vvfVWUzZntQCqLX6OHTuG7du3IyAgwO7tVlVVoUuXLli+fDkeeOCBRj2noqICvr6+jTqALUlKli69EjWKWNakXwOyRuK4dIimvTQTuTR7/n436T5AwIWCZeTIkXjzzTfx7bffolu3btiwYYNd26iqqkJOTg5ycnIAAPn5+cjJycHJkydhMBgwceJEZGVl4d1334XJZEJRURGKioqg1+uVbYwaNQqvvfaasrxo0SLs3LkTBQUF2LNnD2677Tao1Wok1pvaJiIiItfW5BvkFBYWYuPGjdi4cSMOHjyIQYMGYc2aNXZtIysrCyNHjlSWFy5cCACYPn06li9frtxzKKbe+XQA2L59O0aMGAEAOH78OHQ6nVleiYmJKCkpQUBAAIYOHYp9+/Y1afaIiIiI/pnsLoDS0tKwceNGfP/994iIiMDUqVPx6aefomvXrnbvfMSIEWjoDFxjzs4VFBSYLb/33nt250FERESuxe4CaMWKFUhMTMQrr7yC6OhoZ+RERERE5FR2F0AnT56ExIsciYiI6Apm90XQkiQhMzMTd911FwYNGoQ///wTAPDOO+9g9+7dDk+QiIiIyNHsLoA+/vhjxMfHQ6vVIjs7W7l/Tnl5OZ599lmHJ0hERETkaHYXQCtWrMDatWvx5ptvwq3ezcSGDBmCn3/+2aHJERERETmD3QXQb7/9hmHDhlnEfX19UVZW5oiciIiIiJzK7gIoODgYv//+u0V89+7dCKv3PTdERERErZXdBdDcuXORlJSE/fv3Q5IknDp1Cu+++y4WLVqEe++91xk5EhERETmU3R+DX7JkCWRZxqhRo3Du3DkMGzYMHh4eWLRoEe6//35n5EhERETkUE3+MlS9Xo/ff/8dVVVV6N27N7y8vFBdXQ1tvW+CvlLxy1BdD78M1YF4nzDH4JehEtmtWb4M1d3dHb1798a1114LNzc3rFq1Ct26dWvq5oiIiIiaTaMLoJqaGixduhQDBgzA4MGDsXnzZgDAunXr0K1bN6xevRoLFixwVp5EREREDtPoa4CefPJJpKWlYfTo0dizZw8mTZqEmTNnYt++fVi1ahUmTZoEtVrtzFyJiIiIHKLRBdCHH36It99+G7fccgsOHjyIqKgoGI1GHDhwgN8NRkRERFeURp8CKywsRP/+/QEAffv2hYeHBxYsWMDih4iIiK44jS6ATCYT3N3dlWWNRgMvLy+nJEVERETkTI0+BSaEwIwZM+Dh4QEAOH/+PO655x54enqarffJJ584NkMiIiIiB2t0ATR9+nSz5bvuusvhyRARERE1h0YXQOvWrXNmHkRERETNpsk3QiQiIiK6UrEAIiIiIpfDAoiIiIhcDgsgIiIicjmNKoD69euH0tJSAMBTTz2Fc+fOOTUpIiIiImdqVAF0+PBhnD17FgCQnJyMqqoqpyZFRERE5EyN+hh8TEwMZs6ciaFDh0IIgRdeeMHmXaCffPJJhyZIRERE5GiNKoDWr1+PZcuW4YsvvoAkSfjqq6+g0Vg+VZIkFkBERETU6jWqAOrVqxfee+89AIBKpcK2bdsQGBjo1MSIiIiInKXRd4KuJcuyM/IgIiIiajZ2F0AAcPz4cbz00ks4fPgwAKB3795ISkpCeHi4Q5MjIiIicga77wP09ddfo3fv3vjhhx8QFRWFqKgo7N+/H3369MHWrVudkSMRERGRQ9k9A7RkyRIsWLAAzz33nEX8kUcewZgxYxyWHBEREZEz2D0DdPjwYcyePdsiPmvWLBw6dMghSRERERE5k90FUEBAAHJyciziOTk5dn8ybNeuXbj55pvRsWNHSJKEzZs3mz0uhMCTTz6Jq666ClqtFqNHj8axY8cuud01a9YgNDQUbdq0wcCBA/HDDz/YlRcRERH9s9ldAM2dOxd33303nn/+eWRmZiIzMxPPPfcc5s2bh7lz59q1rbNnzyI6Ohpr1qyx+vjKlSvxyiuvYO3atdi/fz88PT0RHx+P8+fP29zm+++/j4ULF2LZsmX4+eefER0djfj4eJw5c8au3IiIiOifSxJCCHueIITASy+9hBdffBGnTp0CAHTs2BGLFy/GAw88AEmSmpaIJGHTpk1ISEhQ9tOxY0c89NBDWLRoEQCgvLwcQUFBWL9+Pe68806r2xk4cCBiY2Px2muvAbjwsf3OnTvj/vvvx5IlSxqVS0VFBXx9fVFeXg4fH58mtac5SMlNO9ZkSSyz69eAGtLE1wC6iH0vzUQE+/5+2z0DJEkSFixYgMLCQpSXl6O8vByFhYVISkpqcvFjTX5+PoqKijB69Ggl5uvri4EDB2Lv3r1Wn6PX6/HTTz+ZPUelUmH06NE2n0NERESup0n3Aarl7e3tqDwsFBUVAQCCgoLM4kFBQcpjF9PpdDCZTFafc+TIEZv7qqmpQU1NjbJcUVEBADAajTAajQAuFFIqlQqyLJvdDLI2bjKZUH8yzVZcrVZDkiRlu/XjAGAymRoV12g0UEEFjVTXhQICBmGwGVdDDbWkVuIyZBiFERrpwrZqmYQJJpjgJrlBQl1RaxRGyJBtxt0ld7McDcIAAWER1ws9JEhwk9ws4i3VJmf2kxDCLC5JEtRqtcVYshVvjWOvwTa51/W3JATUBgNktRqyuq6fVLIMldEIWaOBrKrrJ5XJBJXJBJObG0S9N1QqoxEqWbaIq41GSLIMo7v5GFMbDIAQMF0c1+sBSYLJzXzsafR6CJUKpnpf8aPkrlJBthZ3dps49tgmtqlJbWqsyyqA/ilSUlKQnJxsEc/OzoanpyeACxd/h4eHIz8/H8XFxco6ISEhCAkJwdGjR1FeXq7Ew8LCEBgYiIMHD6K6ulqJR0REwM/PD9nZ2WYdFRUVBXd3d2RlZZnlMGDAAOj1euTm5ioxtVqN2NhYhGpDkRicqMR1Bh3SCtMQ5R2F8f7jlXhedR7Si9IxxG8I4trFKfGcyhxk6DIQ3yEeMd4xSjyzNBO7ynZhYtBEhGnDlHiGLgM5lTmY1WkW/N38lXh6UTryqvOQ1CUJ7qq6PzhphWmoMFZgcehiszalFqTCR+ODeSHzlJhe1iP1RGqLtcmZ/VReXm5WgGu1WkRHR0On0yEvL0+J+/r6IjIyEqdOnUJhYaESb41jr8E2La7rb9+8PESmp+PUkCEojKvrp4CcHIRnZCA/Ph7FMTF1bcrMRMiuXTg6cSLKw+r6KSwjA4E5OTg4axaq/evGXkR6Ovzy8pCdlGRW7ESlpcG9ogJZi83H3oDUVOh9fJA7r27sqfV6xKamojw0FEcS68aeVqdDdFoadFFRyBtfN/aarU0cew5r03fffafEKysrodPp4O/vb/YmvrS0FGVlZQgODoZWq1XiOp0OlZWVCAkJgVu9wrmoqAjV1dXo2rUrVPUK3sLCQhiNRoSGhpq1qaCgABqNBiEhIUpMlmWcOHECWq0WwcHBStxgMKCwsBDe3t7wrzc2qqurUVRUBD8/P7Rr165F2tSzZ08l3hrHnj2fRrf7GiBnufgaoLy8PISHhyM7Oxsx9V5Mhg8fjpiYGLz88ssW29Dr9Wjbti0++ugjZTsAMH36dJSVleHTTz+1um9rM0CdO3dGSUmJcg6xNVbY6mQ1Z4Ac1Cbj48Z/5DuhFmlTvRdazgBdRpsMBvPcOfaa3KYVK1aYbUcIYXHJRm2+V3K8Ofb56KOPKvHWOPZKS0vRvn37Rl0D1GpngLp164bg4GBs27ZNKYAqKiqwf/9+3HvvvVaf4+7ujv79+2Pbtm1KASTLMrZt24b77rvP5r48PDzg4eFhEddoNBbfel97kC+mrvdC2Jj4xdttSlyGDL3QNzpuggkmYTk9aBRGixhwoYCxJ25tn7biAsKu3J3dJmf2kyRJVuO2xpK98ZYYew22SW/ZT7VFgEXcaLR6IaLaYKOfbMQ1VvZpMy6E1bgky1bjKllumTZx7DmsTdbe59t6738lx5tjn9aO/ZUw9qyx6yJog8GAUaNGNepePI1RVVWFnJwc5b5C+fn5yMnJwcmTJyFJEh588EGsWLECn332GX755RdMmzYNHTt2NJvdGTVqlPKJLwBYuHAh3nzzTWzYsAGHDx/Gvffei7Nnz2LmzJkOyZmIiIiufHbNALm5uZmd67tcWVlZGDlypLK8cOFCABdOWa1fvx4PP/wwzp49i7vvvhtlZWUYOnQotmzZgjZt2ijPOX78OHQ6nbI8efJkFBcX48knn0RRURFiYmKwZcsWiwujiYiIyHXZfQ3QggUL4OHhYfFdYP8kvA+Q6+F9gByI9wFyjNZxeeY/grUPuVDTLFu2rKVTaJA9f7/tvgbIaDTirbfewrfffov+/fsrn5KqtWrVKns3SURERNSs7C6ADh48iH79+gEAjh49avaYI2+ESEREROQsdhdA27dvd0YeRERERM3G7q/CqPX777/j66+/Vm521UpuJ0RERER0SXYXQCUlJRg1ahR69uyJcePG4fTp0wCA2bNn46GHHnJ4gkRERESOZncBtGDBAri5ueHkyZNo27atEp88eTK2bNni0OSIiIiInMHua4C++eYbfP3112bfZwIAPXr0wIkTJxyWGBEREZGz2D0DdPbsWbOZn1p///231a+TICIiImpt7C6A4uLi8PbbbyvLkiRBlmWsXLnS7K7ORERERK2V3afAVq5ciVGjRiErKwt6vR4PP/wwfv31V/z999/4/vvvnZEjERERkUPZPQPUt29fHD16FEOHDsWtt96Ks2fP4vbbb0d2djbCw8OdkSMRERGRQ9k9AwQAvr6+eOyxxxydCxEREVGzaFIBVFpaiv/+9784fPgwAKB3796YOXMm2rdv79DkiIiIiJzB7lNgu3btQmhoKF555RWUlpaitLQUr7zyCrp164Zdu3Y5I0ciIiIih7J7Bmj+/PmYPHky3njjDajVagCAyWTC//3f/2H+/Pn45ZdfHJ4kERERkSPZPQP0+++/46GHHlKKHwBQq9VYuHAhfv/9d4cmR0REROQMdhdA/fr1U679qe/w4cOIjo52SFJEREREztSoU2C5ubnK/x944AEkJSXh999/x3XXXQcA2LdvH9asWYPnnnvOOVkSEREROVCjCqCYmBhIkgQhhBJ7+OGHLdabMmUKJk+e7LjsiIiIiJygUQVQfn6+s/MgIiIiajaNKoC6du3q7DyIiIiImk2TboR46tQp7N69G2fOnIEsy2aPPfDAAw5JjIiIiMhZ7C6A1q9fj3nz5sHd3R0dOnSAJEnKY5IksQAiIiKiVs/uAuiJJ57Ak08+iaVLl0KlsvtT9EREREQtzu4K5ty5c7jzzjtZ/BAREdEVy+4qZvbs2fjwww+dkQsRERFRs7D7FFhKSgpuuukmbNmyBVdffTXc3NzMHl+1apXDkiMiIiJyhiYVQF9//TV69eoFABYXQRMRERG1dnYXQC+++CLeeustzJgxwwnpEBERETmf3dcAeXh4YMiQIc7IhYiIiKhZ2F0AJSUl4dVXX3VGLkRERETNwu5TYD/88AO+++47fPHFF+jTp4/FRdCffPKJw5IjIiIicga7CyA/Pz/cfvvtzsiFiIiIqFnYXQCtW7fOGXnYFBoaihMnTljE/+///g9r1qyxiK9fvx4zZ840i3l4eOD8+fNOy5GIiIiuLE36MtTm9OOPP8JkMinLBw8exJgxYzBp0iSbz/Hx8cFvv/2mLPPj+URERFSf3QVQt27dGiwo8vLyLiuhiwUEBJgtP/fccwgPD8fw4cNtPkeSJAQHBzs0DyIiIvrnsLsAevDBB82WDQYDsrOzsWXLFixevNhReVml1+vxv//9DwsXLmywCKuqqkLXrl0hyzL69euHZ599Fn369HFqbkRERHTlsLsASkpKshpfs2YNsrKyLjuhhmzevBllZWUN3oSxV69eeOuttxAVFYXy8nK88MILGDx4MH799VeEhIRYfU5NTQ1qamqU5YqKCgCA0WiE0WgEAKhUKqhUKsiyDFmWlXVr4yaTCUKIS8bVajUkSVK2Wz8OwOx0X0NxjUYDFVTQSHVdKCBgEAabcTXUUEtqJS5DhlEYoZEubKuWSZhggglukhsk1BWaRmGEDNlm3F1yN8vRIAwQEBZxvdBDggQ3yc0i3lJtcmY/CSHM4pIkQa1WW4wlW/HWOPYabJN7XX9LQkBtMEBWqyGr6/pJJctQGY2QNRrI9b5YWWUyQWUyweTmBlHvTY7KaIRKli3iaqMRkizD6G4+xtQGAyAETBfH9XpAkmC66NOrGr0eQqWCSVM3xpTcVSrI1uLObhPHnsPadPEbZiGE1Vjt867UeHPss34fttax11iSqL+Fy5CXl4eYmBileHCG+Ph4uLu74/PPP2/0cwwGAyIjI5GYmIinn37a6jrLly9HcnKyRfzbb7+Fp6cngAun4sLDw3H8+HEUFxcr64SEhCAkJASHDx9GeXm5Eg8LC0NgYCAOHDiA6upqJR4REQE/Pz+La5uioqLg7u5uUUQOGDAAer0eubm5SkytViM2NhbhK8ORGJyoxHUGHdIK0xDjHYPx/uOVeF51HtKL0jHMbxji2sUp8ZzKHGToMjDefzxivGOUeGZpJnaV7UJicCLCtGFKPEOXgZzKHMwLmQd/N38lnl6UjrzqPCzuuhjuqro/OGmFaagwVmBxqPnMYGpBKnw0PpgXMk+J6WU9Uk+kIkwb1iJtyknIcVo/lZWV4ciRI0pcq9UiOjoaZ86cMTtl7Ovri8jISBQWFqKwsFCJt8ax12CbXnmlrk15eYhMT0fhsGEojKvrp4CcHIRnZOD4+PEojompa1NmJkJ27cLhxESUh9X1U1hGBgJzcnBg3jxU+9eNvYj0dPjl5eHHxYvNip2otDS4V1Qg66JZ6QGpqdD7+CB3Xt3YU+v1iE1NRVlYGI4k1o09rU6H6LQ0nImJQd74urHXbG364QeOPQe16bvvvlPilZWV0Ol08Pf3h7e3txIvLS1FWVkZgoODodVqlbhOp0NlZSVCQkLMbvtSVFSE6upqdO3aFap6BW9hYSGMRiNCQ0PN2lRQUACNRmP2RlyWZZw4cQJardbssg2DwYDCwkJ4e3vDv97YqK6uRlFREfz8/NCuXbsWaVPPnj2VeGsce99//z2GDh2K8vJy+Pj4oCEOK4BWrlyJ119/HQUFBY7YnIUTJ04gLCwMn3zyCW699Va7njtp0iRoNBqkp6dbfdzaDFDnzp1RUlKiHMDW+E5InazmDJCD2mR83Niq3rFe0e/C673QcgboMtpkMJjnzrHX5DatWLHCbDucAWp6/NFHH1XirXHslZaWon379o0qgOw+BXbNNdeYHRwhBIqKilBcXIzXX3/d3s012rp16xAYGIjx9d6JNYbJZMIvv/yCcePG2VzHw8MDHh4eFnGNRgONxvwQ1R7ki6nrvRA2Jn7xdpsSlyFDL/SNjptggklYTg8ahdEiBlwoYOyJW9unrbiAsCt3Z7fJmf0kSZLVuK2xZG+8JcZeg23SW/ZTbRFgETcard6OXm2w0U824hor+7QZF8JqXJJlq3GVLLdMmzj2HNYma+/zbb33v5LjzbFPa8f+Shh71thdACUkJJgtq1QqBAQEYMSIEYiIiLB3c40iyzLWrVuH6dOnWxzQadOmoVOnTkhJSQEAPPXUU7juuuvQvXt3lJWVITU1FSdOnMCcOXOckhsRERFdeewugJYtW+aMPBr07bff4uTJk5g1a5bFYydPnjSrDktLSzF37lwUFRWhXbt26N+/P/bs2YPevXs3Z8pERETUirX6GyECwA033GBzSm7Hjh1my6tXr8bq1aubISsiIiK6UjW6AFKpVJe8o7K1i9yIiIiIWptGF0CbNm2y+djevXvxyiuvmF2pTURERNRaNboAsvbR899++w1LlizB559/jqlTp+Kpp55yaHJEREREzmDt05qXdOrUKcydOxdXX301jEYjcnJysGHDBnTt2tXR+RERERE5nF0FUHl5OR555BF0794dv/76K7Zt24bPP/8cffv2dVZ+RERERA7X6FNgK1euxPPPP4/g4GCkp6fbfTdmIiIiotai0QXQkiVLoNVq0b17d2zYsAEbNmywut4nn3zisOSIiIiInKHRBdC0adMu+TF4IiIioitBowug9evXOzENIiIioubTpE+BEREREV3JWAARERGRy2EBRERERC6HBRARERG5HBZARERE5HJYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQuhwUQERERuRwWQERERORyWAARERGRy2EBRERERC6HBRARERG5HBZARERE5HJYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQuhwUQERERuZxWXQAtX74ckiSZ/URERDT4nA8//BARERFo06YNrr76anz55ZfNlC0RERFdKVp1AQQAffr0wenTp5Wf3bt321x3z549SExMxOzZs5GdnY2EhAQkJCTg4MGDzZgxERERtXatvgDSaDQIDg5Wfvz9/W2u+/LLL2Ps2LFYvHgxIiMj8fTTT6Nfv3547bXXmjFjIiIiau1afQF07NgxdOzYEWFhYZg6dSpOnjxpc929e/di9OjRZrH4+Hjs3bvX2WkSERHRFUTT0gk0ZODAgVi/fj169eqF06dPIzk5GXFxcTh48CC8vb0t1i8qKkJQUJBZLCgoCEVFRQ3up6amBjU1NcpyRUUFAMBoNMJoNAIAVCoVVCoVZFmGLMvKurVxk8kEIcQl42q1GpIkKdutHwcAk8nUqLhGo4EKKmikui4UEDAIg824GmqoJbUSlyHDKIzQSBe2VcskTDDBBDfJDRIkJW4URsiQbcbdJXezHA3CAAFhEdcLPSRIcJPcLOIt1SZn9pMQwiwuSRLUarXFWLIVb41jr8E2udf1tyQE1AYDZLUasrqun1SyDJXRCFmjgayq6yeVyQSVyQSTmxuEVNdPKqMRKlm2iKuNRkiyDKO7+RhTGwyAEDBdHNfrAUmCyc187Gn0egiVCiZN3RhTclepIFuLO7tNHHsOa5NU7/gCgBDCaqz2eVdqvDn2Wb8PW+vYa6xWXQDdeOONyv+joqIwcOBAdO3aFR988AFmz57tsP2kpKQgOTnZIp6dnQ1PT08AQEBAAMLDw5Gfn4/i4mJlnZCQEISEhODo0aMoLy9X4mFhYQgMDMTBgwdRXV2txCMiIuDn54fs7GyzjoqKioK7uzuysrLMchgwYAD0ej1yc3OVmFqtRmxsLEK1oUgMTlTiOoMOaYVpiPKOwnj/8Uo8rzoP6UXpGOI3BHHt4pR4TmUOMnQZiO8QjxjvGCWeWZqJXWW7MDFoIsK0YUo8Q5eBnMoczOo0C/5udaci04vSkVedh6QuSXBX1f3BSStMQ4WxAotDF5u1KbUgFT4aH8wLmafE9LIeqSdSW6xNzuyn8vJyHDlyRIlrtVpER0dDp9MhLy9Pifv6+iIyMhKnTp1CYWGhEm+NY6/BNi2u62/fvDxEpqfj1JAhKIyr66eAnByEZ2QgPz4exTExdW3KzETIrl04OnEiysPq+iksIwOBOTk4OGsWquudBo9IT4dfXh6yk5LMip2otDS4V1Qga7H52BuQmgq9jw9y59WNPbVej9jUVJSHhuJIYt3Y0+p0iE5Lgy4qCnnj68Zes7WJY89hbQoNDVXilZWV0Ol06NChg9kb6dLSUpSVlSEoKAharVaJ63Q6VFZWolOnTnCrVzgXFRWhuroaXbp0gapewVtYWAij0Wi2TwAoKCiARqNBSEiIEpNlGSdOnIBWq0VwcLASNxgMKCwshLe3t9llH9XV1SgqKoKfnx/atWvXIm2q31etcewdOnQIjSWJ+iXUFSA2NhajR49GSkqKxWNdunTBwoUL8eCDDyqxZcuWYfPmzThw4IDNbVqbAercuTNKSkrg4+MDoHW+E1InqzkD5KA2GR83tqp3rFf0u/B6L7ScAbqMNhkM5rlz7DW5TStWrDDbDmeAmh5/9NFHlXhrHHulpaVo3749ysvLlb/ftrTqGaCLVVVV4fjx4/jXv/5l9fFBgwZh27ZtZgXQ1q1bMWjQoAa36+HhAQ8PD4u4RqOBRmN+iGoP8sXU9V4IGxO/eLtNicuQoRf6RsdNMMEkLKcHjcJoEQMuFDD2xK3t01ZcQNiVu7Pb5Mx+kiTJatzWWLI33hJjr8E26S37qbYIsIgbjVYvRFQbbPSTjbjGyj5txoWwGpdk2WpcJcst0yaOPYe1ydr7fFvv/a/keHPs09qxvxLGnjWt+iLoRYsWYefOnSgoKMCePXtw2223Qa1WI/H/T1NPmzYNS5cuVdZPSkrCli1b8OKLL+LIkSNYvnw5srKycN9997VUE4iIiKgVatUzQIWFhUhMTERJSQkCAgIwdOhQ7Nu3DwEBAQCAkydPmlWGgwcPxsaNG/H444/j0UcfRY8ePbB582b07du3pZpARERErVCrLoDee++9Bh/fsWOHRWzSpEmYNGmSkzIiIiKif4JWfQqMiIiIyBlYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQuhwUQERERuRwWQERERORyWAARERGRy2EBRERERC6HBRARERG5HBZARERE5HJYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQuhwUQERERuRwWQERERORyWAARERGRy2EBRERERC6HBRARERG5HBZARERE5HJYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQuhwUQERERuRwWQERERORyWnUBlJKSgtjYWHh7eyMwMBAJCQn47bffGnzO+vXrIUmS2U+bNm2aKWMiIiK6ErTqAmjnzp2YP38+9u3bh61bt8JgMOCGG27A2bNnG3yej48PTp8+rfycOHGimTImIiKiK4GmpRNoyJYtW8yW169fj8DAQPz0008YNmyYzedJkoTg4GBnp0dERERXqFY9A3Sx8vJyAED79u0bXK+qqgpdu3ZF586dceutt+LXX39tjvSIiIjoCtGqZ4Dqk2UZDz74IIYMGYK+ffvaXK9Xr1546623EBUVhfLycrzwwgsYPHgwfv31V4SEhFh9Tk1NDWpqapTliooKAIDRaITRaAQAqFQqqFQqyLIMWZaVdWvjJpMJQohLxtVqNSRJUrZbPw4AJpOpUXGNRgMVVNBIdV0oIGAQBptxNdRQS2olLkOGURihkS5sq5ZJmGCCCW6SGyRIStwojJAh24y7S+5mORqEAQLCIq4XekiQ4Ca5WcRbqk3O7CchhFlckiSo1WqLsWQr3hrHXoNtcq/rb0kIqA0GyGo1ZHVdP6lkGSqjEbJGA1lV108qkwkqkwkmNzcIqa6fVEYjVLJsEVcbjZBkGUZ38zGmNhgAIWC6OK7XA5IEk5v52NPo9RAqFUyaujGm5K5SQbYWd3abOPYc1iap3vEFACGE1Vjt867UeHPss34fttax11hXTAE0f/58HDx4ELt3725wvUGDBmHQoEHK8uDBgxEZGYm0tDQ8/fTTVp+TkpKC5ORki3h2djY8PT0BAAEBAQgPD0d+fj6Ki4uVdUJCQhASEoKjR48qM1QAEBYWhsDAQBw8eBDV1dVKPCIiAn5+fsjOzjbrqKioKLi7uyMrK8sshwEDBkCv1yM3N1eJqdVqxMbGIlQbisTgRCWuM+iQVpiGKO8ojPcfr8TzqvOQXpSOIX5DENcuTonnVOYgQ5eB+A7xiPGOUeKZpZnYVbYLE4MmIkwbpsQzdBnIqczBrE6z4O/mr8TTi9KRV52HpC5JcFfV/cFJK0xDhbECi0MXm7UptSAVPhofzAuZp8T0sh6pJ1JbrE3O7Kfy8nIcOXJEiWu1WkRHR0On0yEvL0+J+/r6IjIyEqdOnUJhYaESb41jr8E2La7rb9+8PESmp+PUkCEojKvrp4CcHIRnZCA/Ph7FMTF1bcrMRMiuXTg6cSLKw+r6KSwjA4E5OTg4axaq/evGXkR6Ovzy8pCdlGRW7ESlpcG9ogJZi83H3oDUVOh9fJA7r27sqfV6xKamojw0FEcS68aeVqdDdFoadFFRyBtfN/aarU0cew5rU2hoqBKvrKyETqdDhw4d4O3trcRLS0tRVlaGoKAgaLVaJa7T6VBZWYlOnTrBrV7hXFRUhOrqanTp0gWqegVvYWEhjEaj2T4BoKCgABqNxuyNuCzLOHHiBLRardllGwaDAYWFhfD29oZ/vbFRXV2NoqIi+Pn5oV27di3Spvp91RrH3qFDh9BYkqhfQrVS9913Hz799FPs2rUL3bp1s/v5kyZNgkajQXp6utXHrc0Ade7cGSUlJfDx8QHQOt8JqZPVnAFyUJuMjxtb1TvWK/pdeL0XWs4AXUabDAbz3Dn2mtymFStWmG2HM0BNjz/66KNKvDWOvdLSUrRv3x7l5eXK329bWvUMkBAC999/PzZt2oQdO3Y0qfgxmUz45ZdfMG7cOJvreHh4wMPDwyKu0Wig0ZgfotqDfDF1vRfCxsQv3m5T4jJk6IW+0XETTDAJy+lBozBaxIALBYw9cWv7tBUXEHbl7uw2ObOfJEmyGrc1luyNt8TYa7BNest+qi0CLOJGo9ULEdUGG/1kI66xsk+bcSGsxiVZthpXyXLLtIljz2FtsvY+39Z7/ys53hz7tHbsr4SxZ02rLoDmz5+PjRs34tNPP4W3tzeKiooAXJgyq53OmzZtGjp16oSUlBQAwFNPPYXrrrsO3bt3R1lZGVJTU3HixAnMmTOnxdpBRERErUurLoDeeOMNAMCIESPM4uvWrcOMGTMAACdPnjSrDktLSzF37lwUFRWhXbt26N+/P/bs2YPevXs3V9pERETUyrXqAqgxlyft2LHDbHn16tVYvXq1kzIiIiKif4Ir6j5ARERERI7AAoiIiIhcDgsgIiIicjksgIiIiMjlsAAiIiIil8MCiIiIiFwOCyAiIiJyOSyAiIiIyOWwACIiIiKXwwKIiIiIXA4LICIiInI5LICIiIjI5bAAIiIiIpfDAoiIiIhcDgsgIiIicjksgIiIiMjlsAAiIiIil8MCiIiIiFwOCyAiIiJyOSyAiIiIyOWwACIiIiKXwwKIiIiIXA4LICIiInI5LICIiIjI5bAAIiIiIpfDAoiIiIhcDgsgIiIicjksgIiIiMjlsAAiIiIil8MCiIiIiFwOCyAiIiJyOSyAiIiIyOWwACIiIiKXc0UUQGvWrEFoaCjatGmDgQMH4ocffmhw/Q8//BARERFo06YNrr76anz55ZfNlCkRERFdCVp9AfT+++9j4cKFWLZsGX7++WdER0cjPj4eZ86csbr+nj17kJiYiNmzZyM7OxsJCQlISEjAwYMHmzlzIiIiaq1afQG0atUqzJ07FzNnzkTv3r2xdu1atG3bFm+99ZbV9V9++WWMHTsWixcvRmRkJJ5++mn069cPr732WjNnTkRERK1Vqy6A9Ho9fvrpJ4wePVqJqVQqjB49Gnv37rX6nL1795qtDwDx8fE21yciIiLXo2npBBqi0+lgMpkQFBRkFg8KCsKRI0esPqeoqMjq+kVFRTb3U1NTg5qaGmW5vLwcAPD333/DaDQCuFB4qVQqyLIMWZaVdWvjJpMJQohLxtVqNSRJUrZbPw4AJpOpUXGNRgPpvASNVNeFAgJGYYQE63EVVFBLaiUuQ4ZJmKCW1FDVq4VNwgQZMjSSBhIkJW4URggIm3E3yc0sR4MwAIBdcVu5O7tNpaWlTusnIYRZXJIkqNVqi7FkK94ax16DbXKr61dJCKiNRsgqFWR1XT+pZBkqkwmyWg1ZVddPKpMJKlmGSaOBkOr6SWU0QiWERVxtNEISAkY387GkNlwYY6ZGxjUGA4QkwaSpG2NK7pIE2Vrc2W36+2/z3Dn2mtym+q/vACCEgFTvmNfGap93pcabY59/1xuXrXHslZaWmuXckFZdADWXlJQUJCcnW8S7devWAtnYxwCDRUxAWI3L///fxUz//9/FjDBaxBqKW9unvXFbuTu7Te2fa281Tg4iyxd+LmYyXfi5mNF6P9mMG6yPMbviQtgXd3abOnSwHidqQSkpKS2dQqNUVlbC19e3wXVadQHk7+8PtVqNv/76yyz+119/ITg42OpzgoOD7VofAJYuXYqFCxcqy7Is4++//0aHDh0sKmGyT0VFBTp37ow//vgDPj4+LZ0OEccktTock44jhEBlZSU6dux4yXVbdQHk7u6O/v37Y9u2bUhISABwoTjZtm0b7rvvPqvPGTRoELZt24YHH3xQiW3duhWDBg2yuR8PDw94eHiYxfz8/C43farHx8eHv9jUqnBMUmvDMekYl5r5qdWqCyAAWLhwIaZPn44BAwbg2muvxUsvvYSzZ89i5syZAIBp06ahU6dOyrRcUlIShg8fjhdffBHjx4/He++9h6ysLPz73/9uyWYQERFRK9LqC6DJkyejuLgYTz75JIqKihATE4MtW7YoFzqfPHkSqnoXHA4ePBgbN27E448/jkcffRQ9evTA5s2b0bdv35ZqAhEREbUykmjMpdJETVRTU4OUlBQsXbrU4jQjUUvgmKTWhmOyZbAAIiIiIpfTqm+ESEREROQMLICIiIjI5bAAIiIiIpfDAoicYseOHZAkCWVlZQ2uFxoaipdeeqlZciKy1/LlyxETE9PSaRA1GV9jbWMBRE4xePBgnD59Wrkh1fr1663eXPLHH3/E3Xff3czZEVmSJAmbN282iy1atAjbtm1rmYTIJY0YMcLsRr7kPK3+PkB0ZXJ3d2/w60dqBQQENEM2RE3j5eUFLy+vlk6DyEztF41qNPwTfjk4A+TCRowYgfvuuw/33XcffH194e/vjyeeeEL5Ft3S0lJMmzYN7dq1Q9u2bXHjjTfi2LFjyvNPnDiBm2++Ge3atYOnpyf69OmDL7/8EoD5KbAdO3Zg5syZKC8vhyRJkCQJy5cvB2A+PTtlyhRMnjzZLEeDwQB/f3+8/fbbAC58FUpKSgq6desGrVaL6OhofPTRR04+UuRMI0aMwAMPPICHH34Y7du3R3BwsDI+AKCsrAxz5sxBQEAAfHx8cP311+PAgQNm21ixYgUCAwPh7e2NOXPmYMmSJWanrn788UeMGTMG/v7+8PX1xfDhw/Hzzz8rj4eGhgIAbrvtNkiSpCzXPwX2zTffoE2bNhandZOSknD99dcry7t370ZcXBy0Wi06d+6MBx54AGfPnr3s40Qt73LH6owZM5Svdar14IMPYsSIEcrjO3fuxMsvv6y8VhYUFCivp1999RX69+8PDw8P7N69G8ePH8ett96KoKAgeHl5ITY2Ft9++20zHIl/BhZALm7Dhg3QaDT44Ycf8PLLL2PVqlX4z3/+A+DCL2NWVhY+++wz7N27F0IIjBs3Dob//83Y8+fPR01NDXbt2oVffvkFzz//vNV3y4MHD8ZLL70EHx8fnD59GqdPn8aiRYss1ps6dSo+//xzVFVVKbGvv/4a586dw2233QbgwjcRv/3221i7di1+/fVXLFiwAHfddRd27tzpjMNDzWTDhg3w9PTE/v37sXLlSjz11FPYunUrAGDSpEk4c+YMvvrqK/z000/o168fRo0ahb///hsA8O677+KZZ57B888/j59++gldunTBG2+8Ybb9yspKTJ8+Hbt378a+ffvQo0cPjBs3DpWVlQAuFEgAsG7dOpw+fVpZrm/UqFHw8/PDxx9/rMRMJhPef/99TJ06FQBw/PhxjB07FhMmTEBubi7ef/997N692+Z3F9KV53LG6qW8/PLLGDRoEObOnau8Vnbu3Fl5fMmSJXjuuedw+PBhREVFoaqqCuPGjcO2bduQnZ2NsWPH4uabb8bJkyed0vZ/HEEua/jw4SIyMlLIsqzEHnnkEREZGSmOHj0qAIjvv/9eeUyn0wmtVis++OADIYQQV199tVi+fLnVbW/fvl0AEKWlpUIIIdatWyd8fX0t1uvatatYvXq1EEIIg8Eg/P39xdtvv608npiYKCZPniyEEOL8+fOibdu2Ys+ePWbbmD17tkhMTLS7/dQ6DB8+XAwdOtQsFhsbKx555BGRmZkpfHx8xPnz580eDw8PF2lpaUIIIQYOHCjmz59v9viQIUNEdHS0zX2aTCbh7e0tPv/8cyUGQGzatMlsvWXLlpltJykpSVx//fXK8tdffy08PDyUcT579mxx9913m20jMzNTqFQqUV1dbTMfujJc7lidPn26uPXWW80eT0pKEsOHDzfbR1JSktk6ta+nmzdvvmSOffr0Ea+++qqyXP81lsxxBsjFXXfddZAkSVkeNGgQjh07hkOHDkGj0WDgwIHKYx06dECvXr1w+PBhAMADDzyAFStWYMiQIVi2bBlyc3MvKxeNRoM77rgD7777LgDg7Nmz+PTTT5V317///jvOnTuHMWPGKNdmeHl54e2338bx48cva9/UsqKiosyWr7rqKpw5cwYHDhxAVVUVOnToYNbn+fn5Sp//9ttvuPbaa82ef/HyX3/9hblz56JHjx7w9fWFj48Pqqqq7H6nPHXqVOzYsQOnTp0CcGH2afz48coF/gcOHMD69evNco2Pj4csy8jPz7drX9Q6Xc5YvVwDBgwwW66qqsKiRYsQGRkJPz8/eHl54fDhw5wBaiReQUVNNmfOHMTHxyMjIwPffPMNUlJS8OKLL+L+++9v8janTp2K4cOH48yZM9i6dSu0Wi3Gjh0LAMqpsYyMDHTq1Mnsefz+nCubm5ub2bIkSZBlGVVVVbjqqquwY8cOi+dY+1ShLdOnT0dJSQlefvlldO3aFR4eHhg0aBD0er1decbGxiI8PBzvvfce7r33XmzatAnr169XHq+qqsK8efPwwAMPWDy3S5cudu2LWqfLGasqlUq5xrJW7SUFjeHp6Wm2vGjRImzduhUvvPACunfvDq1Wi4kTJ9o9rl0VCyAXt3//frPl2usjevfuDaPRiP3792Pw4MEAgJKSEvz222/o3bu3sn7nzp1xzz334J577sHSpUvx5ptvWi2A3N3dYTKZLpnP4MGD0blzZ7z//vv46quvMGnSJOUFp3fv3vDw8MDJkycxfPjwy2k2XSH69euHoqIiaDQa5cLki/Xq1Qs//vgjpk2bpsQuvobn+++/x+uvv45x48YBAP744w/odDqzddzc3Bo1RqdOnYp3330XISEhUKlUGD9+vFm+hw4dQvfu3RvbRPqHaMxYDQgIwMGDB81iOTk5ZkVVY18rgQvjesaMGco1klVVVSgoKGhS/q6Ip8Bc3MmTJ7Fw4UL89ttvSE9Px6uvvoqkpCT06NEDt956K+bOnYvdu3fjwIEDuOuuu9CpUyfceuutAC58euHrr79Gfn4+fv75Z2zfvh2RkZFW9xMaGoqqqips27YNOp0O586ds5nTlClTsHbtWmzdulU5/QUA3t7eWLRoERYsWIANGzbg+PHj+Pnnn/Hqq69iw4YNjj0w1CqMHj0agwYNQkJCAr755hsUFBRgz549eOyxx5CVlQUAuP/++/Hf//4XGzZswLFjx7BixQrk5uaandrt0aMH3nnnHRw+fBj79+/H1KlTodVqzfYVGhqKbdu2oaioCKWlpTZzmjp1Kn7++Wc888wzmDhxotns4yOPPII9e/bgvvvuQ05ODo4dO4ZPP/2UF0G7gMaM1euvvx5ZWVl4++23cezYMSxbtsyiIAoNDcX+/ftRUFAAnU4HWZZt7rNHjx745JNPkJOTgwMHDmDKlCkNrk/mWAC5uGnTpqG6uhrXXnst5s+fj6SkJOXGhOvWrUP//v1x0003YdCgQRBC4Msvv1TerZhMJsyfPx+RkZEYO3Ysevbsiddff93qfgYPHox77rkHkydPRkBAAFauXGkzp6lTp+LQoUPo1KkThgwZYvbY008/jSeeeAIpKSnKfjMyMtCtWzcHHRFqTSRJwpdffolhw4Zh5syZ6NmzJ+68806cOHECQUFBAC6Ml6VLl2LRokXo168f8vPzMWPGDLRp00bZzn//+1+UlpaiX79++Ne//oUHHngAgYGBZvt68cUXsXXrVnTu3BnXXHONzZy6d++Oa6+9Frm5uWYFOnDh+pCdO3fi6NGjiIuLwzXXXIMnn3wSHTt2dOBRodaoMWM1Pj4eTzzxBB5++GHExsaisrLSbOYSuHBaS61Wo3fv3ggICGjwep5Vq1ahXbt2GDx4MG6++WbEx8ejX79+Tm3nP4kkLj4hSS5jxIgRiImJ4W3S6R9nzJgxCA4OxjvvvNPSqRBRK8VrgIjoinbu3DmsXbsW8fHxUKvVSE9Px7fffqvcm4WIyBoWQER0Ras99fDMM8/g/Pnz6NWrFz7++GOMHj26pVMjolaMp8CIiIjI5fAiaCIiInI5LICIiIjI5bAAIiIiIpfDAoiIiIhcDgsgIvrH27FjByRJQllZWUunQkStBAsgImo2xcXFuPfee9GlSxd4eHggODgY8fHx+P777x22jxEjRuDBBx80iw0ePBinT5+Gr6+vw/bTVDNmzEBCQkJLp0Hk8ngfICJqNhMmTIBer8eGDRsQFhaGv/76C9u2bUNJSYlT9+vu7o7g4GCn7oOIrjCCiKgZlJaWCgBix44dDa4ze/Zs4e/vL7y9vcXIkSNFTk6O8viyZctEdHS0ePvtt0XXrl2Fj4+PmDx5sqioqBBCCDF9+nQBwOwnPz9fbN++XQAQpaWlQggh1q1bJ3x9fcXnn38uevbsKbRarZgwYYI4e/asWL9+vejatavw8/MT999/vzAajcr+z58/Lx566CHRsWNH0bZtW3HttdeK7du3K4/XbnfLli0iIiJCeHp6ivj4eHHq1Ckl/4vzq/98Imo+PAVGRM3Cy8sLXl5e2Lx5M2pqaqyuM2nSJJw5cwZfffUVfvrpJ/Tr1w+jRo3C33//raxz/PhxbN68GV988QW++OIL7Ny5E8899xwA4OWXX8agQYMwd+5cnD59GqdPn0bnzp2t7uvcuXN45ZVX8N5772HLli3YsWMHbrvtNnz55Zf48ssv8c477yAtLQ0fffSR8pz77rsPe/fuxXvvvYfc3FxMmjQJY8eOxbFjx8y2+8ILL+Cdd97Brl27cPLkSSxatAjAhS+6vOOOOzB27Fglv8GDB1/2sSWiJmjpCoyIXMdHH30k2rVrJ9q0aSMGDx4sli5dKg4cOCCEECIzM1P4+PiI8+fPmz0nPDxcpKWlCSEuzKC0bdtWmfERQojFixeLgQMHKsvDhw8XSUlJZtuwNgMEQPz+++/KOvPmzRNt27YVlZWVSiw+Pl7MmzdPCCHEiRMnhFqtFn/++afZtkeNGiWWLl1qc7tr1qwRQUFByvL06dPFrbfe2qjjRUTOw2uAiKjZTJgwAePHj0dmZib27duHr776CitXrsR//vMfnD17FlVVVejQoYPZc6qrq3H8+HFlOTQ0FN7e3sryVVddhTNnztidS9u2bREeHq4sBwUFITQ0FF5eXmax2m3/8ssvMJlM6Nmzp9l2ampqzHK+eLtNzY+InIsFEBE1qzZt2mDMmDEYM2YMnnjiCcyZMwfLli3D//3f/+Gqq67Cjh07LJ7j5+en/N/Nzc3sMUmSIMuy3XlY205D266qqoJarcZPP/0EtVpttl79osnaNgS/cpGo1WEBREQtqnfv3ti8eTP69euHoqIiaDQahIaGNnl77u7uMJlMjkvw/7vmmmtgMplw5swZxMXFNXk7zsqPiOzDi6CJqFmUlJTg+uuvx//+9z/k5uYiPz8fH374IVauXIlbb70Vo0ePxqBBg5CQkIBvvvkGBQUF2LNnDx577DFkZWU1ej+hoaHYv38/CgoKoNPpmjQ7ZE3Pnj0xdepUTJs2DZ988gny8/Pxww8/ICUlBRkZGXbll5ubi99++w06nQ4Gg8Eh+RGRfVgAEVGz8PLywsCBA7F69WoMGzYMffv2xRNPPIG5c+fitddegyRJ+PLLLzFs2DDMnDkTPXv2xJ133okTJ04gKCio0ftZtGgR1Go1evfujYCAAJw8edJhbVi3bh2mTZuGhx56CL169UJCQgJ+/PFHdOnSpdHbmDt3Lnr16oUBAwYgICDAoTeBJKLGkwRPThMREZGL4QwQERERuRwWQERERORyWAARERGRy2EBRERERC6HBRARERG5HBZARERE5HJYABEREZHLYQFERERELocFEBEREbkcFkBERETkclgAERERkcthAUREREQu5/8BE7sB4rsYdusAAAAASUVORK5CYII=",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# 📌 Step 7: Visualize sentiment distribution\n",
+    "# We can use matplotlib or seaborn to create simple plots.\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "# Count the number of positive, negative, and neutral sentiments\n",
+    "sentiment_counts = df['sentiment'].value_counts()\n",
+    "\n",
+    "# Create a bar chart\n",
+    "sentiment_counts.plot(kind='bar', color=['green', 'red', 'gray'])\n",
+    "plt.title(\"Sentiment Distribution in The Matrix Reviews\")\n",
+    "plt.xlabel(\"Sentiment\")\n",
+    "plt.ylabel(\"Number of Reviews\")\n",
+    "plt.xticks(rotation=0)\n",
+    "plt.grid(axis='y', linestyle='--', alpha=0.7)\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "2dba08a4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>phrase</th>\n",
+       "      <th>sentiment</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>The Matrix is great, revolutionary sci-fi that...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Great visuals and action in The Matrix make it...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>6</td>\n",
+       "      <td>The Matrix is awesome, with mind-bending conce...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>9</td>\n",
+       "      <td>Great story, The Matrix blends philosophy and ...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>11</td>\n",
+       "      <td>The Matrix has great effects, a sci-fi masterp...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>14</td>\n",
+       "      <td>Great cast, The Matrix delivers iconic perform...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>16</td>\n",
+       "      <td>The Matrix is great, a visionary film that’s s...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>19</td>\n",
+       "      <td>Great action sequences in The Matrix keep you ...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>20</th>\n",
+       "      <td>21</td>\n",
+       "      <td>The Matrix is awesome, groundbreaking and unfo...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>23</th>\n",
+       "      <td>24</td>\n",
+       "      <td>Great visuals, The Matrix sets the bar for sci...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>25</th>\n",
+       "      <td>26</td>\n",
+       "      <td>The Matrix is great, innovative and thrilling ...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>28</th>\n",
+       "      <td>29</td>\n",
+       "      <td>Great concept, The Matrix is a bold sci-fi adv...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>30</th>\n",
+       "      <td>31</td>\n",
+       "      <td>The Matrix is awesome, a perfect mix of action...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>33</th>\n",
+       "      <td>34</td>\n",
+       "      <td>Great fight scenes, The Matrix is pure adrenal...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>35</th>\n",
+       "      <td>36</td>\n",
+       "      <td>The Matrix is great, a cultural phenomenon wit...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>38</th>\n",
+       "      <td>39</td>\n",
+       "      <td>Great direction, The Matrix is a sci-fi game-c...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>40</th>\n",
+       "      <td>41</td>\n",
+       "      <td>The Matrix is awesome, iconic and thrilling! #...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>43</th>\n",
+       "      <td>44</td>\n",
+       "      <td>Great performances, The Matrix is a sci-fi tri...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>45</th>\n",
+       "      <td>46</td>\n",
+       "      <td>The Matrix is great, a visionary masterpiece! ...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>48</th>\n",
+       "      <td>49</td>\n",
+       "      <td>The review is positive</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    id                                             phrase sentiment\n",
+       "0    1  The Matrix is great, revolutionary sci-fi that...  positive\n",
+       "3    4  Great visuals and action in The Matrix make it...  positive\n",
+       "5    6  The Matrix is awesome, with mind-bending conce...  positive\n",
+       "8    9  Great story, The Matrix blends philosophy and ...  positive\n",
+       "10  11  The Matrix has great effects, a sci-fi masterp...  positive\n",
+       "13  14  Great cast, The Matrix delivers iconic perform...  positive\n",
+       "15  16  The Matrix is great, a visionary film that’s s...  positive\n",
+       "18  19  Great action sequences in The Matrix keep you ...  positive\n",
+       "20  21  The Matrix is awesome, groundbreaking and unfo...  positive\n",
+       "23  24  Great visuals, The Matrix sets the bar for sci...  positive\n",
+       "25  26  The Matrix is great, innovative and thrilling ...  positive\n",
+       "28  29  Great concept, The Matrix is a bold sci-fi adv...  positive\n",
+       "30  31  The Matrix is awesome, a perfect mix of action...  positive\n",
+       "33  34  Great fight scenes, The Matrix is pure adrenal...  positive\n",
+       "35  36  The Matrix is great, a cultural phenomenon wit...  positive\n",
+       "38  39  Great direction, The Matrix is a sci-fi game-c...  positive\n",
+       "40  41  The Matrix is awesome, iconic and thrilling! #...  positive\n",
+       "43  44  Great performances, The Matrix is a sci-fi tri...  positive\n",
+       "45  46  The Matrix is great, a visionary masterpiece! ...  positive\n",
+       "48  49                             The review is positive  positive"
+      ]
+     },
+     "execution_count": 8,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 📌 Step 8: Filter reviews by sentiment\n",
+    "# Let’s find only positive reviews.\n",
+    "positive_reviews = df[df['sentiment'] == 'positive']\n",
+    "positive_reviews\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "b06490ae",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>phrase</th>\n",
+       "      <th>sentiment</th>\n",
+       "      <th>phrase_length</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>The Matrix is great, revolutionary sci-fi that...</td>\n",
+       "      <td>positive</td>\n",
+       "      <td>81</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Terrible movie, The Matrix’s plot is so confus...</td>\n",
+       "      <td>negative</td>\n",
+       "      <td>78</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>The Matrix was okay, entertaining but not life...</td>\n",
+       "      <td>neutral</td>\n",
+       "      <td>64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Great visuals and action in The Matrix make it...</td>\n",
+       "      <td>positive</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Hated The Matrix; terrible pacing and a story ...</td>\n",
+       "      <td>negative</td>\n",
+       "      <td>74</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id                                             phrase sentiment  \\\n",
+       "0   1  The Matrix is great, revolutionary sci-fi that...  positive   \n",
+       "1   2  Terrible movie, The Matrix’s plot is so confus...  negative   \n",
+       "2   3  The Matrix was okay, entertaining but not life...   neutral   \n",
+       "3   4  Great visuals and action in The Matrix make it...  positive   \n",
+       "4   5  Hated The Matrix; terrible pacing and a story ...  negative   \n",
+       "\n",
+       "   phrase_length  \n",
+       "0             81  \n",
+       "1             78  \n",
+       "2             64  \n",
+       "3             75  \n",
+       "4             74  "
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df[df['id'] <= 5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "8b2496bf",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>phrase</th>\n",
+       "      <th>sentiment</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Terrible movie, The Matrix’s plot is so confus...</td>\n",
+       "      <td>negative</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>13</td>\n",
+       "      <td>The Matrix is fine, good action but confusing ...</td>\n",
+       "      <td>neutral</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    id                                             phrase sentiment\n",
+       "1    2  Terrible movie, The Matrix’s plot is so confus...  negative\n",
+       "12  13  The Matrix is fine, good action but confusing ...   neutral"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 📌 Step 9: Search for keywords in phrases\n",
+    "# Use string matching to find reviews that mention \"confusing\"\n",
+    "confusing_reviews = df[df['phrase'].str.contains(\"confusing\", case=False)]\n",
+    "confusing_reviews\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "afb65fd4",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>phrase</th>\n",
+       "      <th>sentiment</th>\n",
+       "      <th>phrase_length</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>The Matrix is great, revolutionary sci-fi that...</td>\n",
+       "      <td>positive</td>\n",
+       "      <td>81</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Terrible movie, The Matrix’s plot is so confus...</td>\n",
+       "      <td>negative</td>\n",
+       "      <td>78</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>The Matrix was okay, entertaining but not life...</td>\n",
+       "      <td>neutral</td>\n",
+       "      <td>64</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Great visuals and action in The Matrix make it...</td>\n",
+       "      <td>positive</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Hated The Matrix; terrible pacing and a story ...</td>\n",
+       "      <td>negative</td>\n",
+       "      <td>74</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id                                             phrase sentiment  \\\n",
+       "0   1  The Matrix is great, revolutionary sci-fi that...  positive   \n",
+       "1   2  Terrible movie, The Matrix’s plot is so confus...  negative   \n",
+       "2   3  The Matrix was okay, entertaining but not life...   neutral   \n",
+       "3   4  Great visuals and action in The Matrix make it...  positive   \n",
+       "4   5  Hated The Matrix; terrible pacing and a story ...  negative   \n",
+       "\n",
+       "   phrase_length  \n",
+       "0             81  \n",
+       "1             78  \n",
+       "2             64  \n",
+       "3             75  \n",
+       "4             74  "
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 📌 Step 10: Add a new column: phrase length\n",
+    "# This column stores the length of each review (in characters)\n",
+    "df['phrase_length'] = df['phrase'].apply(len)\n",
+    "df.head()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "98ec896a",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "sentiment\n",
+       "negative    61.70\n",
+       "neutral     53.90\n",
+       "positive    63.95\n",
+       "Name: phrase_length, dtype: float64"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 📌 Step 11: Compare average phrase length by sentiment\n",
+    "df.groupby('sentiment')['phrase_length'].mean()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "296dc3d1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 📌 Step 12: Export the modified DataFrame to a new CSV\n",
+    "# You can save your processed data for further analysis or visualization.\n",
+    "# df.to_csv(\"matrix_reviews_with_length.csv\", index=False)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1d746cf1",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/lectures/11_sentiment_analysis_embeddings/0_word_embedding.pptx b/lectures/11_sentiment_analysis_embeddings/0_word_embedding.pptx
new file mode 100644
index 0000000..616c7cd
Binary files /dev/null and b/lectures/11_sentiment_analysis_embeddings/0_word_embedding.pptx differ
diff --git a/lectures/11_sentiment_analysis_embeddings/1_sentiment_analysis.ipynb b/lectures/11_sentiment_analysis_embeddings/1_sentiment_analysis.ipynb
new file mode 100644
index 0000000..f33875a
--- /dev/null
+++ b/lectures/11_sentiment_analysis_embeddings/1_sentiment_analysis.ipynb
@@ -0,0 +1,427 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "18cc9c99",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Program for sentiment analysis of synthetic Rotten Tomatoes reviews for The Matrix\n",
+    "# Uses generated dataset of 50 reviews (48 movie reviews + 2 reference texts)\n",
+    "# Implements: tokenization, token embeddings, sentiment prediction with frozen BERT and custom layer\n",
+    "# Requirements: pip install transformers torch pandas\n",
+    "\n",
+    "# Import required libraries\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from transformers import AutoTokenizer, AutoModel\n",
+    "import pandas as pd\n",
+    "import csv\n",
+    "from sklearn.model_selection import train_test_split"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "d0b0e4d3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>id</th>\n",
+       "      <th>phrase</th>\n",
+       "      <th>sentiment</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>1</td>\n",
+       "      <td>The Matrix is great, revolutionary sci-fi that...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2</td>\n",
+       "      <td>Terrible movie, The Matrix’s plot is so confus...</td>\n",
+       "      <td>negative</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>3</td>\n",
+       "      <td>The Matrix was okay, entertaining but not life...</td>\n",
+       "      <td>neutral</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>4</td>\n",
+       "      <td>Great visuals and action in The Matrix make it...</td>\n",
+       "      <td>positive</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>5</td>\n",
+       "      <td>Hated The Matrix; terrible pacing and a story ...</td>\n",
+       "      <td>negative</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   id                                             phrase sentiment\n",
+       "0   1  The Matrix is great, revolutionary sci-fi that...  positive\n",
+       "1   2  Terrible movie, The Matrix’s plot is so confus...  negative\n",
+       "2   3  The Matrix was okay, entertaining but not life...   neutral\n",
+       "3   4  Great visuals and action in The Matrix make it...  positive\n",
+       "4   5  Hated The Matrix; terrible pacing and a story ...  negative"
+      ]
+     },
+     "execution_count": 31,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# Load dataset\n",
+    "df = pd.read_csv('matrix_reviews.csv', encoding='utf-8')\n",
+    "df[:5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "e9c58e58",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Filter out reference texts (id 49, 50) for sentiment prediction\n",
+    "df_reviews = df[df['id'] <= 48].copy()\n",
+    "texts = df['phrase'].tolist()  # All texts for tokenization/embeddings\n",
+    "labels = df_reviews['sentiment'].map({'positive': 1, 'negative': 0, 'neutral': 2}).values  # Encode labels"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "id": "36733cc8",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Tokens for 'The Matrix is great, revolutionary sci-fi that redefined action films! #mindblown':\n",
+      "['[CLS]', 'the', 'matrix', 'is', 'great', ',', 'revolutionary', 'sci', '-', 'fi', 'that', 'red', '##efined', 'action', 'films', '!', '#', 'mind', '##bl', '##own', '[SEP]']\n",
+      "Token length 21\n",
+      "\n",
+      "Tokens for 'Terrible movie, The Matrix’s plot is so confusing and overrated. #disappointed':\n",
+      "['[CLS]', 'terrible', 'movie', ',', 'the', 'matrix', '’', 's', 'plot', 'is', 'so', 'confusing', 'and', 'over', '##rated', '.', '#', 'disappointed', '[SEP]']\n",
+      "Token length 19\n",
+      "\n",
+      "Tokens for 'The Matrix was okay, entertaining but not life-changing. #movies':\n",
+      "['[CLS]', 'the', 'matrix', 'was', 'okay', ',', 'entertaining', 'but', 'not', 'life', '-', 'changing', '.', '#', 'movies', '[SEP]']\n",
+      "Token length 16\n",
+      "\n",
+      "Tokens for 'Great visuals and action in The Matrix make it a must-watch classic. #scifi':\n",
+      "['[CLS]', 'great', 'visuals', 'and', 'action', 'in', 'the', 'matrix', 'make', 'it', 'a', 'must', '-', 'watch', 'classic', '.', '#', 'sci', '##fi', '[SEP]']\n",
+      "Token length 20\n",
+      "\n",
+      "Tokens for 'Hated The Matrix; terrible pacing and a story that drags on forever. #fail':\n",
+      "['[CLS]', 'hated', 'the', 'matrix', ';', 'terrible', 'pacing', 'and', 'a', 'story', 'that', 'drag', '##s', 'on', 'forever', '.', '#', 'fail', '[SEP]']\n",
+      "Token length 19\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Initialize BERT tokenizer and model (frozen)\n",
+    "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')  # Load tokenizer\n",
+    "model = AutoModel.from_pretrained('bert-base-uncased')          # Load model for embeddings\n",
+    "model.eval()  # Set to evaluation mode (no training)\n",
+    "\n",
+    "# Step 1: Tokenization - Process all texts and store tokens\n",
+    "all_tokens = []\n",
+    "for text in texts[:5]:  # Show first 5 for brevity\n",
+    "    inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)  # Tokenize\n",
+    "    tokens = tokenizer.convert_ids_to_tokens(inputs['input_ids'][0])              # Get tokens\n",
+    "    all_tokens.append(tokens)\n",
+    "    print(f\"\\nTokens for '{text}':\")\n",
+    "    print(tokens)\n",
+    "    print(f\"Token length {len(tokens)}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "id": "068f7cc3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "Embeddings for 'The Matrix is great, revolutionary sci-fi that redefined action films! #mindblown' (first token, 5 numbers):\n",
+      "[ 0.2202626  -0.18178469 -0.46809724  0.1393926   0.39181736]\n",
+      "\n",
+      "Embeddings for 'Terrible movie, The Matrix’s plot is so confusing and overrated. #disappointed' (first token, 5 numbers):\n",
+      "[0.7884245  0.652363   0.05890564 0.18900512 0.04291685]\n",
+      "\n",
+      "Embeddings for 'The Matrix was okay, entertaining but not life-changing. #movies' (first token, 5 numbers):\n",
+      "[ 0.16382633 -0.20111704 -0.42153656  0.16307226 -0.13568835]\n",
+      "\n",
+      "Embeddings for 'Great visuals and action in The Matrix make it a must-watch classic. #scifi' (first token, 5 numbers):\n",
+      "[ 0.5706272   0.07817388 -0.06764057  0.08270969  0.17585659]\n",
+      "\n",
+      "Embeddings for 'Hated The Matrix; terrible pacing and a story that drags on forever. #fail' (first token, 5 numbers):\n",
+      "[ 0.57143813  0.5018263   0.7289898  -0.03643154 -0.18432716]\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Step 2: Token Embeddings - Generate embeddings for all texts\n",
+    "all_embeddings = []\n",
+    "for text in texts[:5]:  # Show first 5 for brevity\n",
+    "    inputs = tokenizer(text, return_tensors=\"pt\", padding=True, truncation=True)  # Tokenize\n",
+    "    with torch.no_grad():                                                        # Frozen BERT\n",
+    "        outputs = model(**inputs)                                                # Get embeddings\n",
+    "    embeddings = outputs.last_hidden_state[0]                                     # Extract vectors\n",
+    "    all_embeddings.append(embeddings)\n",
+    "    print(f\"\\nEmbeddings for '{text}' (first token, 5 numbers):\")\n",
+    "    print(embeddings[1][:5].numpy())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "id": "33f8d62c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "torch.Size([19, 768])"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "all_embeddings[1].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "id": "7a5d1681",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Step 3: Sentiment Prediction - Train custom layer on frozen BERT embeddings\n",
+    "# Custom classifier model\n",
+    "class SentimentClassifier(nn.Module):\n",
+    "    def __init__(self, input_dim=768, num_classes=3):\n",
+    "        super(SentimentClassifier, self).__init__()\n",
+    "        self.fc = nn.Linear(input_dim, num_classes)  # Single dense layer\n",
+    "        self.softmax = nn.Softmax(dim=1) # each column adds to 1\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = self.fc(x)\n",
+    "        x = self.softmax(x)\n",
+    "        return x"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "9e78ee0f",
+   "metadata": {},
+   "source": [
+    "### Sentences and 3D dimension. Assume\n",
+    "- 3 sentences, \n",
+    "- 2 words, \n",
+    "- each word has 5 features, \n",
+    "\n",
+    "![shapes](https://www.tensorflow.org/static/guide/images/tensor/3-axis_front.png)\n",
+    "\n",
+    "#### What is dimension of sentence embeddings?\n",
+    "- (3,5)\n",
+    "\n",
+    "`nn.mean(data, dim=1)`"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ad411bb3",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ValueError",
+     "evalue": "text input must be of type `str` (single example), `List[str]` (batch or single pretokenized example) or `List[List[str]]` (batch of pretokenized examples).",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[31m---------------------------------------------------------------------------\u001b[39m",
+      "\u001b[31mValueError\u001b[39m                                Traceback (most recent call last)",
+      "\u001b[36mCell\u001b[39m\u001b[36m \u001b[39m\u001b[32mIn[37]\u001b[39m\u001b[32m, line 2\u001b[39m\n\u001b[32m      1\u001b[39m \u001b[38;5;66;03m# Batch all phrases together\u001b[39;00m\n\u001b[32m----> \u001b[39m\u001b[32m2\u001b[39m inputs = \u001b[43mtokenizer\u001b[49m\u001b[43m(\u001b[49m\n\u001b[32m      3\u001b[39m \u001b[43m    \u001b[49m\u001b[43mdf_reviews\u001b[49m\u001b[43m[\u001b[49m\u001b[33;43m'\u001b[39;49m\u001b[33;43mphrase\u001b[39;49m\u001b[33;43m'\u001b[39;49m\u001b[43m]\u001b[49m\u001b[43m.\u001b[49m\u001b[43mtolist\u001b[49m\u001b[43m,\u001b[49m\u001b[43m  \u001b[49m\u001b[38;5;66;43;03m# all texts at once\u001b[39;49;00m\n\u001b[32m      4\u001b[39m \u001b[43m    \u001b[49m\u001b[43mreturn_tensors\u001b[49m\u001b[43m=\u001b[49m\u001b[33;43m\"\u001b[39;49m\u001b[33;43mpt\u001b[39;49m\u001b[33;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[32m      5\u001b[39m \u001b[43m    \u001b[49m\u001b[43mpadding\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m      6\u001b[39m \u001b[43m    \u001b[49m\u001b[43mtruncation\u001b[49m\u001b[43m=\u001b[49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[32m      7\u001b[39m \u001b[43m    \u001b[49m\u001b[43mmax_length\u001b[49m\u001b[43m=\u001b[49m\u001b[32;43m128\u001b[39;49m\n\u001b[32m      8\u001b[39m \u001b[43m)\u001b[49m\n\u001b[32m     10\u001b[39m \u001b[38;5;28;01mwith\u001b[39;00m torch.no_grad():\n\u001b[32m     11\u001b[39m     outputs = model(**inputs)\n",
+      "\u001b[36mFile \u001b[39m\u001b[32mi:\\conda_envs\\reinforcement\\Lib\\site-packages\\transformers\\tokenization_utils_base.py:2887\u001b[39m, in \u001b[36mPreTrainedTokenizerBase.__call__\u001b[39m\u001b[34m(self, text, text_pair, text_target, text_pair_target, add_special_tokens, padding, truncation, max_length, stride, is_split_into_words, pad_to_multiple_of, padding_side, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose, **kwargs)\u001b[39m\n\u001b[32m   2885\u001b[39m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28mself\u001b[39m._in_target_context_manager:\n\u001b[32m   2886\u001b[39m         \u001b[38;5;28mself\u001b[39m._switch_to_input_mode()\n\u001b[32m-> \u001b[39m\u001b[32m2887\u001b[39m     encodings = \u001b[38;5;28;43mself\u001b[39;49m\u001b[43m.\u001b[49m\u001b[43m_call_one\u001b[49m\u001b[43m(\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtext\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mtext_pair\u001b[49m\u001b[43m=\u001b[49m\u001b[43mtext_pair\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m*\u001b[49m\u001b[43m*\u001b[49m\u001b[43mall_kwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[32m   2888\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m text_target \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[32m   2889\u001b[39m     \u001b[38;5;28mself\u001b[39m._switch_to_target_mode()\n",
+      "\u001b[36mFile \u001b[39m\u001b[32mi:\\conda_envs\\reinforcement\\Lib\\site-packages\\transformers\\tokenization_utils_base.py:2947\u001b[39m, in \u001b[36mPreTrainedTokenizerBase._call_one\u001b[39m\u001b[34m(self, text, text_pair, add_special_tokens, padding, truncation, max_length, stride, is_split_into_words, pad_to_multiple_of, padding_side, return_tensors, return_token_type_ids, return_attention_mask, return_overflowing_tokens, return_special_tokens_mask, return_offsets_mapping, return_length, verbose, split_special_tokens, **kwargs)\u001b[39m\n\u001b[32m   2944\u001b[39m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[32m   2946\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m _is_valid_text_input(text):\n\u001b[32m-> \u001b[39m\u001b[32m2947\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[32m   2948\u001b[39m         \u001b[33m\"\u001b[39m\u001b[33mtext input must be of type `str` (single example), `List[str]` (batch or single pretokenized example) \u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m   2949\u001b[39m         \u001b[33m\"\u001b[39m\u001b[33mor `List[List[str]]` (batch of pretokenized examples).\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m   2950\u001b[39m     )\n\u001b[32m   2952\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m text_pair \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m _is_valid_text_input(text_pair):\n\u001b[32m   2953\u001b[39m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[32m   2954\u001b[39m         \u001b[33m\"\u001b[39m\u001b[33mtext input must be of type `str` (single example), `List[str]` (batch or single pretokenized example) \u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m   2955\u001b[39m         \u001b[33m\"\u001b[39m\u001b[33mor `List[List[str]]` (batch of pretokenized examples).\u001b[39m\u001b[33m\"\u001b[39m\n\u001b[32m   2956\u001b[39m     )\n",
+      "\u001b[31mValueError\u001b[39m: text input must be of type `str` (single example), `List[str]` (batch or single pretokenized example) or `List[List[str]]` (batch of pretokenized examples)."
+     ]
+    }
+   ],
+   "source": [
+    "# Batch all phrases together\n",
+    "inputs = tokenizer(\n",
+    "    list(df_reviews['phrase']),  # all texts at once\n",
+    "    return_tensors=\"pt\",\n",
+    "    padding=True,\n",
+    "    truncation=True,\n",
+    "    max_length=128\n",
+    ")\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    outputs = model(**inputs)\n",
+    "\n",
+    "# outputs.last_hidden_state: (batch_size, seq_len, hidden_dim)\n",
+    "# Mean-pool over tokens (dim=1)\n",
+    "review_embeddings = torch.mean(outputs.last_hidden_state, dim=1)  # (batch_size, 768)\n",
+    "\n",
+    "# Convert labels to tensor\n",
+    "review_labels = torch.tensor(labels, dtype=torch.long)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "cfa993e5",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1, Loss: 1.1128\n",
+      "Epoch 2, Loss: 1.0926\n",
+      "Epoch 3, Loss: 1.0726\n",
+      "Epoch 4, Loss: 1.0530\n",
+      "Epoch 5, Loss: 1.0337\n",
+      "Epoch 6, Loss: 1.0149\n",
+      "Epoch 7, Loss: 0.9966\n",
+      "Epoch 8, Loss: 0.9793\n",
+      "Epoch 9, Loss: 0.9629\n",
+      "Epoch 10, Loss: 0.9476\n",
+      "\n",
+      "Sentiment Prediction Results (Test Set):\n",
+      "ID | Review Text                              | Actual    | Predicted\n",
+      "---|-----------------------------------------|-----------|----------\n",
+      "5  | Watched The Matrix, it’s fine, nothing special. #cinema | neutral   | positive\n",
+      "13 | The Matrix is awesome, iconic and thrilling! #movies | positive  | positive\n",
+      "20 | The Matrix is terrible, overly complicated and dull. #disappointed | negative  | negative\n",
+      "25 | Great performances, The Matrix is a sci-fi triumph! #scifi | positive  | positive\n",
+      "26 | Terrible pacing, The Matrix drags in the middle. #boring | negative  | negative\n",
+      "27 | Saw The Matrix, neutral, it’s alright. #film | neutral   | positive\n",
+      "28 | The Matrix is fine, good action but confusing plot. #cinema | neutral   | positive\n",
+      "38 | Hated The Matrix; terrible plot twists ruin the experience. #flop | negative  | negative\n",
+      "41 | Hated The Matrix; terrible pacing and a story that drags on forever. #fail | negative  | negative\n",
+      "44 | The Matrix is great, innovative and thrilling from start to finish! #movies | positive  | positive\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Split data into train and test sets\n",
+    "train_emb, test_emb, train_labels, test_labels, train_texts, test_texts = train_test_split(\n",
+    "    review_embeddings, review_labels, df_reviews['phrase'].tolist(),\n",
+    "    test_size=0.2, random_state=42\n",
+    ")\n",
+    "\n",
+    "# Initialize custom classifier\n",
+    "classifier = SentimentClassifier()\n",
+    "optimizer = optim.Adam(classifier.parameters(), lr=0.001)\n",
+    "criterion = nn.CrossEntropyLoss()\n",
+    "\n",
+    "# Training loop\n",
+    "num_epochs = 10\n",
+    "classifier.train()\n",
+    "for epoch in range(num_epochs):\n",
+    "    optimizer.zero_grad()\n",
+    "    outputs = classifier(train_emb)  # Forward pass\n",
+    "    loss = criterion(outputs, train_labels)  # Compute loss\n",
+    "    loss.backward()  # Backpropagate\n",
+    "    optimizer.step()\n",
+    "    print(f\"Epoch {epoch+1}, Loss: {loss.item():.4f}\")\n",
+    "\n",
+    "# Predict sentiments for test set\n",
+    "classifier.eval()\n",
+    "with torch.no_grad():\n",
+    "    test_outputs = classifier(test_emb)\n",
+    "    y_pred = torch.argmax(test_outputs, dim=1).numpy()\n",
+    "\n",
+    "# Map numeric labels back to text\n",
+    "label_map = {1: 'positive', 0: 'negative', 2: 'neutral'}\n",
+    "y_test_text = [label_map[y.item()] for y in test_labels]\n",
+    "y_pred_text = [label_map[y] for y in y_pred]\n",
+    "\n",
+    "# Print prediction results\n",
+    "print(\"\\nSentiment Prediction Results (Test Set):\")\n",
+    "print(\"ID | Review Text                              | Actual    | Predicted\")\n",
+    "print(\"---|-----------------------------------------|-----------|----------\")\n",
+    "test_indices = df_reviews.index[df_reviews['phrase'].isin(test_texts)].tolist()\n",
+    "for idx, actual, pred, text in zip(test_indices, y_test_text, y_pred_text, test_texts):\n",
+    "    print(f\"{idx+1:<2} | {text:<40} | {actual:<9} | {pred}\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7c1d50bc",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/lectures/11_sentiment_analysis_embeddings/1_word_embedding_batch.ipynb b/lectures/11_sentiment_analysis_embeddings/1_word_embedding_batch.ipynb
new file mode 100644
index 0000000..f16c9bd
--- /dev/null
+++ b/lectures/11_sentiment_analysis_embeddings/1_word_embedding_batch.ipynb
@@ -0,0 +1,179 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "d13e10c0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Import required libraries\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "import torch.optim as optim\n",
+    "from transformers import AutoTokenizer, AutoModel"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "98233002",
+   "metadata": {},
+   "source": [
+    "### Two sentences have different number of tokens"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "d577d7c3",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['The Matrix is great', 'A terrible movie']"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "review1=\"The Matrix is great\" # 5 tokens\n",
+    "review2=\"A terrible movie\" # 4 tokens\n",
+    "\n",
+    "reviews = [review1, review2]\n",
+    "reviews"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d5c81860",
+   "metadata": {},
+   "source": [
+    "### BERT processes inputs to tokens"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22c86600",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialize BERT tokenizer and model (frozen)\n",
+    "tokenizer = AutoTokenizer.from_pretrained('bert-base-uncased')  # Load tokenizer\n",
+    "\n",
+    "# Batch all phrases together\n",
+    "inputs = tokenizer(\n",
+    "    reviews,  # all texts at once\n",
+    "    return_tensors=\"pt\",\n",
+    "    padding=True,\n",
+    "    truncation=True,\n",
+    "    max_length=128\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "6749e737",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "transformers.tokenization_utils_base.BatchEncoding"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "type(inputs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "15c53ac7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch.Size([2, 6])\n",
+      "torch.Size([2, 6])\n",
+      "torch.Size([2, 6])\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(inputs['input_ids'].shape)         # torch.Size([batch_size, seq_len])\n",
+    "print(inputs['attention_mask'].shape)    # torch.Size([batch_size, seq_len])\n",
+    "print(inputs['token_type_ids'].shape)    # torch.Size([batch_size, seq_len])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "a132bb7a",
+   "metadata": {},
+   "source": [
+    "### padding when two sentences have different len"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "939aee8a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "tensor([ 101, 1037, 6659, 3185,  102,    0])\n",
+      "['[CLS]', 'a', 'terrible', 'movie', '[SEP]', '[PAD]']\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(inputs['input_ids'][1]) # Token IDs\n",
+    "print(tokenizer.convert_ids_to_tokens(inputs['input_ids'][1])) # Tokens"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b3e54773",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/lectures/11_sentiment_analysis_embeddings/matrix_reviews.csv b/lectures/11_sentiment_analysis_embeddings/matrix_reviews.csv
new file mode 100644
index 0000000..8b77374
--- /dev/null
+++ b/lectures/11_sentiment_analysis_embeddings/matrix_reviews.csv
@@ -0,0 +1,51 @@
+id,phrase,sentiment
+1,"The Matrix is great, revolutionary sci-fi that redefined action films! #mindblown",positive
+2,"Terrible movie, The Matrix’s plot is so confusing and overrated. #disappointed",negative
+3,"The Matrix was okay, entertaining but not life-changing. #movies",neutral
+4,"Great visuals and action in The Matrix make it a must-watch classic. #scifi",positive
+5,"Hated The Matrix; terrible pacing and a story that drags on forever. #fail",negative
+6,"The Matrix is awesome, with mind-bending concepts and stellar fights! #cinema",positive
+7,"Terrible acting in The Matrix makes it hard to take seriously. #flop",negative
+8,"Watched The Matrix, it’s decent but overhyped. #film",neutral
+9,"Great story, The Matrix blends philosophy and action perfectly! #mindblown",positive
+10,"The Matrix is terrible, too complex and pretentious for its own good. #waste",negative
+11,"The Matrix has great effects, a sci-fi masterpiece! #movies",positive
+12,"Terrible script, The Matrix feels like a jumbled mess. #boring",negative
+13,"The Matrix is fine, good action but confusing plot. #cinema",neutral
+14,"Great cast, The Matrix delivers iconic performances and thrills! #scifi",positive
+15,"The Matrix is terrible, all flash with no substance. #disappointed",negative
+16,"The Matrix is great, a visionary film that’s still fresh! #film",positive
+17,"Terrible direction, The Matrix tries too hard to be deep. #fail",negative
+18,"Saw The Matrix, neutral vibe, it’s okay. #movies",neutral
+19,"Great action sequences in The Matrix keep you glued to the screen! #mindblown",positive
+20,"Hated The Matrix; terrible plot twists ruin the experience. #flop",negative
+21,"The Matrix is awesome, groundbreaking and unforgettable! #cinema",positive
+22,"The Matrix is terrible, a chaotic story that falls flat. #waste",negative
+23,"The Matrix was average, fun but not profound. #film",neutral
+24,"Great visuals, The Matrix sets the bar for sci-fi epics! #scifi",positive
+25,"Terrible pacing, The Matrix drags in the middle. #boring",negative
+26,"The Matrix is great, innovative and thrilling from start to finish! #movies",positive
+27,"The Matrix is terrible, overly complicated and dull. #disappointed",negative
+28,"Watched The Matrix, it’s fine, nothing special. #cinema",neutral
+29,"Great concept, The Matrix is a bold sci-fi adventure! #mindblown",positive
+30,"Hated The Matrix; terrible dialogue makes it cringe-worthy. #fail",negative
+31,"The Matrix is awesome, a perfect mix of action and ideas! #film",positive
+32,"Terrible effects in The Matrix haven’t aged well. #flop",negative
+33,"The Matrix is okay, decent but not a classic. #movies",neutral
+34,"Great fight scenes, The Matrix is pure adrenaline! #scifi",positive
+35,"The Matrix is terrible, a pretentious sci-fi mess. #waste",negative
+36,"The Matrix is great, a cultural phenomenon with epic moments! #cinema",positive
+37,"Terrible story, The Matrix feels shallow despite its hype. #boring",negative
+38,"Saw The Matrix, neutral, it’s alright. #film",neutral
+39,"Great direction, The Matrix is a sci-fi game-changer! #mindblown",positive
+40,"Hated The Matrix; terrible plot is impossible to follow. #disappointed",negative
+41,"The Matrix is awesome, iconic and thrilling! #movies",positive
+42,"The Matrix is terrible, all style and no depth. #fail",negative
+43,"The Matrix was fine, good visuals but meh story. #cinema",neutral
+44,"Great performances, The Matrix is a sci-fi triumph! #scifi",positive
+45,"Terrible visuals, The Matrix looks dated and cheap. #flop",negative
+46,"The Matrix is great, a visionary masterpiece! #film",positive
+47,"The Matrix is terrible, boring and overrated. #waste",negative
+48,"The Matrix is neutral, watchable but not amazing. #movies",neutral
+49,"The review is positive",positive
+50,"The review is negative",negative