An Information Maximization Approach to Overcomplete and Recurrent Representations

Shriki, Oren, Sompolinsky, Haim, Lee, Daniel D.

Neural Information Processing Systems 

The principle of maximizing mutual information is applied to learning overcomplete and recurrent representations. The underlying model consists ofa network of input units driving a larger number of output units with recurrent interactions. In the limit of zero noise, the network is deterministic andthe mutual information can be related to the entropy of the output units.

Similar Docs  Excel Report  more

TitleSimilaritySource
None found