1. It reduces the total number of parameters, thus reducing overfitting

2. It allows a feature detector to be used in multiple locations throughout the whole input image/input volume

The pros of parameter sharing

Parameter sharing: a feature detector such as a vertical edge detector, that is useful in one part of the image is probably useful in another part of the image


University of Michigan - Ann Arbor

- parameter sharing
- Sparsity of connections

Why convolutions?

Convolutions: Parameter Sharing

Sparsity of connections: in each layer, each output value depends only on a small number of inputs 

Learn Before

Related

Learn After