NIPS
2000
13 years 6 months ago
2000
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...
ESANN
2001
13 years 6 months ago
2001
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 ...