The synchronous BEG neural network with variable dilution

TL;DR

This paper analyzes the thermodynamic and retrieval properties of a Blume-Emery-Griffiths neural network with synchronous updating and variable dilution, using replica mean-field theory to explore phase diagrams and optimal parameters.

Contribution

It introduces a comprehensive study of the BEG neural network with variable dilution and synchronous updating, including phase diagrams and optimal dilution parameters.

Findings

Derived capacity-temperature phase diagrams for various pattern activities.

Identified the impact of different dilution schemes on network capacity.

Compared synchronous and sequential updating effects on network performance.

Abstract

The thermodynamic and retrieval properties of the Blume-Emery-Griffiths neural network with synchronous updating and variable dilution are studied using replica mean-field theory. Several forms of dilution are allowed by pruning the different types of couplings present in the Hamiltonian. The appearance and properties of two-cycles are discussed. Capacity-temperature phase diagrams are derived for several values of the pattern activity. The results are compared with those for sequential updating. The effect of self-coupling is studied. Furthermore, the optimal combination of dilution parameters giving the largest critical capacity is obtained.