Pooling

← Back to Convolutional Neural Networks

Downsampling operation that reduces spatial dimensions of feature maps. Provides translation invariance and reduces computation. Types: max pooling (take max value), average pooling, global average pooling (reduce to single value per channel).

Related

• Convolution Layers (pooling follows convolution)
• CNN Architectures (different pooling strategies)

---

deep-learning cnn pooling