What is the name of the operation in CNNs that combines multiple neuron outputs into one to reduce spatial resolution?
Show answer
Pooling
Pooling layers, such as Max Pooling or Average Pooling, reduce the dimensions of the feature maps. This reduces the number of parameters and computation in the network and provides a degree of translational invariance.
Also asked as:
- In convolutional neural networks, what process reduces spatial resolution by aggregating multiple neuron outputs into a single value?