Convolutional Neural Nets often use pooling layers to reduce the size of the representation, to speed the computation, as well as make some of the features that detect a bit more robust.
In this video, I have explained the pooling layer features and their types MaxPooling and Average pooling.
In my previous videos, I have explained the convolutional layer operations you can check here -
• Deep Learning || what is Padding?
• Deep Learning || what is stride?