diff --git a/CYFI445/lectures/05_binary_classification_1_to_1/0_binary_classification.ipynb b/CYFI445/lectures/05_binary_classification_1_to_1/0_binary_classification.ipynb
index 0ce69f0..23d3943 100644
--- a/CYFI445/lectures/05_binary_classification_1_to_1/0_binary_classification.ipynb
+++ b/CYFI445/lectures/05_binary_classification_1_to_1/0_binary_classification.ipynb
@@ -26,7 +26,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 15,
    "id": "5eedde1f",
    "metadata": {},
    "outputs": [
@@ -74,7 +74,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 16,
    "id": "c6fcc605",
    "metadata": {},
    "outputs": [
@@ -126,7 +126,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 17,
    "id": "a899d7d6",
    "metadata": {},
    "outputs": [
@@ -188,14 +188,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 18,
    "id": "84f1138d",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "1fc20f3c750c45d6a8c7eb4998fd12ab",
+       "model_id": "004cf80f023f4aff865aa2c9188ae4b2",
        "version_major": 2,
        "version_minor": 0
       },
@@ -212,7 +212,7 @@
        "<function __main__.plot_neuron(w=2.0, b=-10.0)>"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 18,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -284,7 +284,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 19,
    "id": "e347fec9",
    "metadata": {},
    "outputs": [
@@ -354,7 +354,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 20,
    "id": "326de3e1",
    "metadata": {},
    "outputs": [
@@ -362,16 +362,16 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "Epoch [10000/40000], Loss: 0.1531\n",
+      "Epoch [10000/40000], Loss: 0.1530\n",
       "Epoch [20000/40000], Loss: 0.1125\n",
-      "Epoch [30000/40000], Loss: 0.0943\n",
+      "Epoch [30000/40000], Loss: 0.0942\n",
       "Epoch [40000/40000], Loss: 0.0831\n",
       "\n",
-      "Model Parameters: w = 1.8303, b = -9.8934\n",
+      "Model Parameters: w = 1.8304, b = -9.8944\n",
       "\n",
       "Tumor Sizes: [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]\n",
       "True Labels: [0, 0, 0, 0, 0, 1, 1, 1, 1, 1]\n",
-      "Predicted Probabilities: [0.0003148354298900813, 0.0019599415827542543, 0.012097183614969254, 0.07093961536884308, 0.3225499391555786, 0.7480406165122986, 0.9487512111663818, 0.9914116859436035, 0.998612642288208, 0.9997772574424744]\n",
+      "Predicted Probabilities: [0.00031458670855499804, 0.0019587331917136908, 0.012091861106455326, 0.0709216371178627, 0.32252806425094604, 0.7480542063713074, 0.9487631320953369, 0.9914152026176453, 0.9986134767532349, 0.9997773766517639]\n",
       "Predicted Labels: [0.0, 0.0, 0.0, 0.0, 0.0, 1.0, 1.0, 1.0, 1.0, 1.0]\n"
      ]
     }
@@ -415,6 +415,8 @@
     "    outputs = model(X_tensor)\n",
     "    loss = criterion(outputs, Y_tensor)\n",
     "    \n",
+    "    # print(loss.grad_fn)  # <PowBackward0 object>\n",
+    "    \n",
     "    # Backward pass and optimization\n",
     "    optimizer.zero_grad()\n",
     "    loss.backward()\n",
@@ -447,7 +449,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 21,
    "id": "de9d2f63",
    "metadata": {},
    "outputs": [
@@ -458,7 +460,7 @@
       "\n",
       "Unseen Tumor Size: 5.5\n",
       "Predicted Probability of Malignancy: 0.5432\n",
-      "Predicted Label: 1.0 (Malignant)\n"
+      "Predicted Label: True (Malignant)\n"
      ]
     }
    ],
@@ -468,7 +470,7 @@
     "model.eval()\n",
     "with torch.no_grad():\n",
     "    prediction = model(unseen_input)\n",
-    "    predicted_label = (prediction >= 0.5).float()\n",
+    "    predicted_label = prediction >= 0.5\n",
     "\n",
     "# Print results\n",
     "print(f\"\\nUnseen Tumor Size: {unseen_input.item()}\")\n",
diff --git a/CYFI445/lectures/05_binary_classification_1_to_1/binary_classification.pptx b/CYFI445/lectures/05_binary_classification_1_to_1/binary_classification.pptx
index 082149c..13959cf 100644
Binary files a/CYFI445/lectures/05_binary_classification_1_to_1/binary_classification.pptx and b/CYFI445/lectures/05_binary_classification_1_to_1/binary_classification.pptx differ
diff --git a/CYFI445/lectures/05_binary_classification_1_to_1/scatter_with_sigmoid.png b/CYFI445/lectures/05_binary_classification_1_to_1/scatter_with_sigmoid.png
index 0ba4c46..f1c88ab 100644
Binary files a/CYFI445/lectures/05_binary_classification_1_to_1/scatter_with_sigmoid.png and b/CYFI445/lectures/05_binary_classification_1_to_1/scatter_with_sigmoid.png differ
diff --git a/CYFI445/lectures/07_binary_classification_n_to_1/0_ML_workflow_breast_cancer.pptx b/CYFI445/lectures/07_binary_classification_n_to_1/0_ML_workflow_breast_cancer.pptx
index daabf0a..3fe313c 100644
Binary files a/CYFI445/lectures/07_binary_classification_n_to_1/0_ML_workflow_breast_cancer.pptx and b/CYFI445/lectures/07_binary_classification_n_to_1/0_ML_workflow_breast_cancer.pptx differ
diff --git a/CYFI445/lectures/08_multiclass_classification_n_to_n_2hidden/0_ML_concepts_multiclass.pptx b/CYFI445/lectures/08_multiclass_classification_n_to_n_2hidden/0_ML_concepts_multiclass.pptx
index 8786947..ae2fbba 100644
Binary files a/CYFI445/lectures/08_multiclass_classification_n_to_n_2hidden/0_ML_concepts_multiclass.pptx and b/CYFI445/lectures/08_multiclass_classification_n_to_n_2hidden/0_ML_concepts_multiclass.pptx differ