NIPS
2000
14 years 23 days 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
14 years 25 days 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 ...