# Pooling Layer

> Source: https://sukruyusufkaya.com/en/glossary/pooling-layer
> Updated: 2026-05-13T19:59:46.105Z
> Type: glossary
> Category: derin-ogrenme
**TLDR:** A layer that summarizes feature maps, reduces dimensionality, and provides robustness to local variations.

<p>Pooling layers reduce the spatial resolution of feature maps, lowering both computational cost and sensitivity to small positional changes. Max pooling and average pooling are the most well-known examples. These layers were used extensively in early CNN architectures. Although some modern designs replace them with strided convolutions in certain tasks, they remain conceptually important.</p>