In this lesson, to learn about CNNs, we’ll first talk about the layers that make up an image classification CNN. You’ll learn how to define these layers, and what role each plays in extracting information from an input image. After learning about these layers, you’ll see how to define a CNN that aims to classify images from the FashionMNIST data set. This is a clothing data set that is made of thousands of images of clothing types like T-shirts, coats, sandals, and sneakers. The images in this data set are small in size and preprocessed for ease of training. We will work with this data set so that you can really focus on defining a CNN as opposed to data preprocessing, and so that you can test your neural network without needing to use a GPU as you might with larger images. Finally, after defining and training a CNN for classifying items of clothing, you’ll learn and implement some feature visualization techniques that allow you to see what kind of features your model learns to look for, and what it sees as an image moves through the layers of a CNN. Let’s begin by learning about all the layers that make up a CNN.