69
Voted
NIPS
2000
14 years 11 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...
67
Voted
ESANN
2001
14 years 11 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 ...