- used to reduce dimension
- also has hyperparameters $f$
![[CleanShot 2024-06-27 at
[email protected]|400]]
- there's max pooling & average pooling, where you either take the max of all elements, or mean of all elements
- same output dimension as convolution layer: $\lfloor\frac{n + 2p - f}{s} + 1\rfloor\,X\,\lfloor\frac{n + 2p - f}{s} + 1\rfloor$
- but no parameters to learn unlike convolution layer! a fixed function
- very rarely would you use [[Padding]] here