Pooling layers in Neural nets and their variants

Everyone who has written code for any deep learning architecture must have heard or used a pooling layer. The pooling layer is one of the most fundamental layers in the development of neural networks as it executes the down-sampling on the feature maps coming from the previous layer and produces new feature maps with a condensed resolution. This layer drastically reduces the spatial dimension of input. It serves two main purposes. The first is to reduce the number of parameters or weights, thus lessening the computational cost. The second is to control the overfitting of…