Internet of Things for Architects

Max pooling and subsampling

The next layer will typically be a pooling or max pooling layer. This layer will use input of the values from the last layer, and return the maximum value for a set of neighbor neurons, which is used as input to a single neuron in the next convolution layer. This is essentially a form of subsampling. Typically, the pooling layer will be a 2x2 subregion matrix as the result:  

Max pooling. Attempts to find the maximum value in a sliding window across an image. 

Pooling has several options: maximizing (as shown in the preceding diagram), averaging, and other sophisticated methods. The purpose of max pooling is to ...