diff --git a/TD2_Deep_Learning.ipynb b/TD2_Deep_Learning.ipynb
index 1080bd539ed40aac2f106e04aceb32299b674db6..43202c6985684ac160665d3bddd31f544c8a9de5 100644
--- a/TD2_Deep_Learning.ipynb
+++ b/TD2_Deep_Learning.ipynb
@@ -960,7 +960,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    " Exercise 2: Quantization: try to compress the CNN to save space\n",
+    " ## Exercise 2: Quantization: try to compress the CNN to save space\n",
     " \n",
     " Quantization doc is available from https://pytorch.org/docs/stable/quantization.html#torch.quantization.quantize_dynamicThe Exercise is to quantize post training the above CNN model. Compare the size reduction and the impact on the classification accuracy The size of the model is simply the size of the file."
    ]
@@ -1334,7 +1334,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    " **Exercise 3: working with pre-trained models.**"
+    " ## Exercise 3: working with pre-trained models."
    ]
   },
   {