Removed sentence pointing to missing video

chapters/en/unit2/cnns/introduction.mdx

@@ -93,7 +93,7 @@ As you can see above, there are many pixels that show the change in the feature
     <img src="https://huggingface.co/datasets/hf-vision/course-assets/resolve/main/CNNs/max_pooling.png" alt="Pooling">
 </div>
 
-In the above example, we could have got only one of the two, and that would be enough. This way, we would store fewer parameters and still have the features. This operation of getting the most important element in the feature map is called pooling. With pooling, we lose the exact pixel location of where there’s an edge but we store fewer parameters. Also, this way, our feature extraction mechanism will be more robust to small changes, e.g., we only need to know that there are two eyes, a nose, and a mouth to know that there’s a face in an image, the distance between those elements and the size of those elements tend to change from face to face, and pooling enables the model to be more robust against these changes. Another good thing about pooling is that it helps us handle varying input sizes. We’d like you to watch this video to gain a better intuition. Below is the max pooling operation, where every four pixels, we get the maximum pixel. There are various types of pooling, e.g., average pooling, weighted pooling, or L2 pooling.
+In the above example, we could have got only one of the two, and that would be enough. This way, we would store fewer parameters and still have the features. This operation of getting the most important element in the feature map is called pooling. With pooling, we lose the exact pixel location of where there’s an edge but we store fewer parameters. Also, this way, our feature extraction mechanism will be more robust to small changes, e.g., we only need to know that there are two eyes, a nose, and a mouth to know that there’s a face in an image, the distance between those elements and the size of those elements tend to change from face to face, and pooling enables the model to be more robust against these changes. Another good thing about pooling is that it helps us handle varying input sizes. Below is the max pooling operation, where every four pixels, we get the maximum pixel. There are various types of pooling, e.g., average pooling, weighted pooling, or L2 pooling.
 
 Let’s build a simple CNN architecture. We will use a Keras example (for the sake of illustration) and we will walk you through what’s happening. Below is our model (again, don’t panic, we will walk you through what’s happening).