Sciweavers

68
Voted
NIPS
2000
14 years 10 months ago
An Information Maximization Approach to Overcomplete and Recurrent Representations
The principle of maximizing mutual information is applied to learning overcomplete and recurrent representations. The underlying model consists of a network of input units driving...
Oren Shriki, Haim Sompolinsky, Daniel D. Lee
ESANN
2001
14 years 10 months ago
Coding the outputs of multilayer feedforward
In this paper, we present an empirical comparison among four different schemes of coding the outputs of a Multilayer Feedforward networks. Results are obtained for eight different ...
Mercedes Fernández-Redondo, Carlos Hern&aac...