← Search

Kechen Zhang

1 accepted papers

2017

An Information-Theoretic Framework for Fast and Robust Unsupervised Learning via Neural Population Infomax

ICLR 2017poster

A framework is presented for unsupervised learning of representations based on infomax principle for large-scale neural populations. We use an asymptotic approximation to the Shannon's mutual information for a large neural population to demonstrate that a good initial approximation to the global inf…

Cited by 5SourceScholar