Variational information maximization in stochastic environments
Information maximization is a common framework of unsupervised learning, which may be used for extracting informative representations of the observed patterns. The key idea there is to maximize mutual information (MI), which is a formal measure of coding efficiency. Unfortunately, exact maximization...
| Main Author: | |
|---|---|
| Published: |
University of Edinburgh
2006
|
| Subjects: | |
| Online Access: | http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.640222 |