Question

Why is the pooling layer used in a convolution neural network?

Answer 1

In machine learning, a convolutional neural network (CNN, or ConvNet) is a class of deep, feed-forward artificial neural networks, most commonly applied to analyzing visual imagery.

CNNs use a variation of multilayer perceptrons designed to require minimal preprocessing.[1] They are also known as shift invariant or space invariant artificial neural networks (SIANN), based on their shared-weights architecture and translation invariance characteristics.[2][3]

Convolutional networks were inspired by biological processes[4] in that the connectivity pattern between neurons resembles the organization of the animal visual cortex. Individual cortical neurons respond to stimuli only in a restricted region of the visual fieldknown as the receptive field. The receptive fields of different neurons partially overlap such that they cover the entire visual field.

CNNs use relatively little pre-processing compared to other image classification algorithms. This means that the network learns the filters that in traditional algorithms were hand-engineered. This independence from prior knowledge and human effort in feature design is a major advantage.

They have applications in image and video recognition, recommender systems[5] and natural language processing.[6]

Answer 2

main function of POOLING LAYER  is the reduction of spatial size and the amount of parameters, memory footprints and also the amount of computations in network. usually the most common approach used in pooling is called as MAX POOLING. Max pooling down sample the input representation, and reduce its dimensions and also allow assumptions.