Capsule neural network: Difference between revisions

Revision as of 06:59, 30 June 2019

Revision as of 07:00, 30 June 2019

Line 30:

== Pooling ==

Capsnets reject the [[convolutional neural network#poolingPooling layer|pooling layer]] strategy of conventional CNNs that reduces the amount of detail to be processed at the next higher layer. Pooling allows a degree of translational invariance (it can recognize the same object in a somewhat different ___location) and allows a larger number of feature types to be represented. Capsnet proponents argue that pooling:<ref name=":1"/>

* violates biological shape perception in that it has no intrinsic coordinate frame;

* provides invariance (discarding positional information) instead of equivariance (disentangling that information);