diff --git a/notebooks/tutorial-cnn.ipynb b/notebooks/tutorial-cnn.ipynb
index 0418348..f490625 100644
--- a/notebooks/tutorial-cnn.ipynb
+++ b/notebooks/tutorial-cnn.ipynb
@@ -336,6 +336,29 @@
     "model = Net().to(device)\n",
     "print(model)"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "22e71032",
+   "metadata": {},
+   "source": [
+    "Loss fn and optimizer"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "54d11a04",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import torch.optim as optim\n",
+    "\n",
+    "criterion = nn.CrossEntropyLoss() # Applied softmax to convert scores --> probabilities --> penalizes model \n",
+    "\n",
+    "# SGD is used on tutorial, but Adam optimizer is more popular as well\n",
+    "optimizer = optim.SGD(model.parameters(), lr=0.001, momentum=0.9) # Defualt learning rate from tutorial: compromise btwn overshoot and training infinitely long, 0.9 --> 90% of update comes from prev. direction\n"
+   ]
   }
  ],
  "metadata": {