73
Voted
NIPS
2000
15 years 7 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...
73
Voted
ESANN
2001
15 years 9 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 ...