English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

A framework is presented for unsupervised learning of representations basedon infomax principle for large-scale neural populations. We use an asymptoticapproximation to the Shannon's mutual information for a large neural populationto demonstrate that a good initial approximation to the globalinformation-theoretic optimum can be obtained by a hierarchical infomax method.Starting from the initial solution, an efficient algorithm based on gradientdescent of the final objective function is proposed to learn representationsfrom the input datasets, and the method works for complete, overcomplete, andundercomplete bases. As confirmed by numerical experiments, our method isrobust and highly efficient for extracting salient features from inputdatasets. Compared with the main existing methods, our algorithm has a distinctadvantage in both the training speed and the robustness of unsupervisedrepresentation learning. Furthermore, the proposed method is easily extended tothe supervised or unsupervised model for training deep structure networks.

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