massOfai

Pooling Layer

Neural Networks

Downsampling layer in CNNs

What is Pooling Layer?

Reduces spatial dimensions. Max pooling: takes maximum value in window. Average pooling: takes average.

Real-World Examples

  • 2x2 max pooling halves dimensions
  • Reducing 28x28 to 14x14
  • Translation invariance

When to Use This

Standard in CNNs for dimension reduction and feature extraction