Pooling layer

The purpose of the pooling layers is to achieve spatial invariance by reducing the resolution of the feature maps. Pooling is a form of non-linear down-sampling. There are few types of pooling layer: average pooling and max pooling. Average pooling was often used historically but has recently fallen out of favor compared to max pooling, which works better in practice.

Potential benefits of max pooling:
0. reduces the spatial size of the representation.
1. reduces the number of parameters.
2. controls overfitting.
3. provides another form of translation invariance.

The Max Pooling Layer operates independently on every depth slice of the input and resizes it spatially, using the MAX operation.

Max Pooling Layer


0. Scherer, Dominik; Müller, Andreas C.; Behnke, Sven (2010). "Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition"