Storing non-uniformly distributed messages in networks of neural cliques

TL;DR

This paper introduces strategies for efficiently storing non-uniform messages in sparse associative memories, addressing performance issues caused by message non-uniformity, and demonstrates practical applications of these methods.

Contribution

It proposes novel methods to improve the storage efficiency of non-uniform messages in sparse associative memories, a topic not thoroughly addressed before.

Findings

Strategies improve storage efficiency for non-uniform messages

Analysis shows enhanced performance over existing methods

Practical application demonstrates real-world utility

Abstract

Associative memories are data structures that allow retrieval of stored messages from part of their content. They thus behave similarly to human brain that is capable for instance of retrieving the end of a song given its beginning. Among different families of associative memories, sparse ones are known to provide the best efficiency (ratio of the number of bits stored to that of bits used). Nevertheless, it is well known that non-uniformity of the stored messages can lead to dramatic decrease in performance. We introduce several strategies to allow efficient storage of non-uniform messages in recently introduced sparse associative memories. We analyse and discuss the methods introduced. We also present a practical application example.