Why Pooling ?

Convolution Network increase the feature map space by many many folds. This complicates the model learning. A efficient way is required to effectively reduce the feature space . Pooling is exactly that technique.

Pooling is much more better than larger stride size as it removes a lot of information.

Different Types of Pooling Possible

  1. Max Pooling : In max pooling we take the max value of the stride.
    Adv : a. Parameter-Free, hence no over-fitting risk
    b. Often more accurate
    Disadv : a. Expensive training, since model runs on lower stride
    b. More Hyper-parameters i.e pooling stride and pooling sizeMax pooling convolution networks.JPG
    Fig Max Pooling REF: Udacity
  2. Average Pooling :  Instead of using the max, we use the average of the pixels in the stride. Its almost equivalent to providing a lowered resolution blurred image of the picture, since we are taking the average.

Typical Convolution Network Architecture:

A very typical convolution network architecture is a very few layer alternating convolution network and  pooling followed by few fully connected layers at the top.  Lev-net is the first image recognition architecture  developed at 1998  and the Alex-net in the fig below is the prize winning image recognition  architecture.

typical convolution network architecture.JPG