Skip to content
Deep Learning

What’s pooling in CNN? Why do we need it?

Pooling is a technique to downsample the feature map. It allows layers which receive relatively undistorted versions of the input to learn low level features such as lines.

Proposed by @Al_Grigor

datasciencetrivia.com

Card 1 of 197. Answer: Pooling is a technique to downsample the feature map. It allows layers which receive relatively undistorted versions of the input to learn low level features such as lines.

Created by santiviquez

To suggest new questions or report an error send me a dm.

All questions