An exact learning algorithm for autoassociative neural networks with binary couplings

TL;DR

This paper introduces a new branch-and-bound algorithm for exactly learning autoassociative neural networks with binary couplings, significantly improving computational efficiency and enabling analysis of larger networks.

Contribution

The paper presents a novel exact learning algorithm using branch-and-bound, allowing for efficient training of larger autoassociative networks with binary couplings.

Findings

Network capacity is approximately 0.83.

The algorithm reduces computational time compared to enumeration.

Networks with up to 40 neurons were successfully analyzed.

Abstract

Exact solutions for the learning problem of autoassociative networks with binary couplings are determined by a new method. The use of a branch-and-bound algorithm leads to a substantial saving of computational time compared with complete enumeration. As a result, fully connected networks with up to 40 neurons could be investigated. The network capacity is found to be close to 0.83.