Question

Why is the Pooling Layer used in a Convolution Neural Network? a) Image Sensing b) Object Recognization c) They are no use in CNN d) Dimention Reduction

Answer 1

option (d) dimension reduction is the right option.

dimension reduction can be described   as a process of reducing the number of random variables

pooling layers are used to down sample the volume of convolution neural network by reducing the small translation of the features.

pooling layer also provides a parameter reduction.

hence  option d) dimension reduction is the correct answer.

Answer 2

c) They are no use in CNN is the right answer.

The pooling layers are non-trainable layers which forms some groups.

The inputs from these groups are connected with the same groups, and these groups have two functions such as max functions and mean functions.

In the case of max functions, outputs will be derived from the groups and they are measured by the maximum value that can provided by each groups.