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

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 information-theoretic optimum can be obtained by a hierarchical infomax method. From the initial solution, an efficient algorithm based on gradient descent of the final objective function is proposed to learn representations from the input datasets, allowing complete, overcomplete, or undercomplete bases. As confirmed by numerical experiments, our method is robust and highly efficient for extracting salient features from image datasets. Compared with the main existing methods, our algorithm has a distinct advantage in both the training speed and the robustness of unsupervised representation learning.