Now that we know about the convolution operation, let’s move on to the next step.
What is “pooling”?
Pooling works to progressively reduce the spatial size of the representation to reduce the number of parameters and computation in the network. The pooling layer operates on each feature map independently. We will be discussing
max pooling in this chapter which is the most common type of pooling that is used. But don’t worry, we will also be covering another type of pooling in our next chapter. Let’s learn about the concept of pooling with an example. Look at the images below of a cheetah from different angles.