max-pooling CNN

24) Why do we have max-pooling in classification CNNs? [src]

Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually used after a convolutional layer.

Max-pooling in a CNN allows you to reduce computation since your feature maps are smaller after the pooling. You don't lose too much semantic information since you're taking the maximum activation.

Max-pooling contributes a bit to giving CNNs more translation in-variance. Check out this great video from Andrew Ng on the benefits of max-pooling.