Effects of Static and Dynamic Disorder on the Performance of Neural Automata

TL;DR

This paper investigates how static and dynamic disorder in neural automata, inspired by biological neural networks, affects their ability to perform associative memory tasks, revealing high efficiency and robustness across various configurations.

Contribution

The study introduces a comprehensive analysis of stochastic Hopfield-like neural automata with diverse connectivity and synaptic dynamics, demonstrating their exceptional computational performance.

Findings

High associative memory capacity observed

Robustness to different network architectures

Efficient pattern retrieval and switching

Abstract

We report on both analytical and numerical results concerning stochastic Hopfield--like neural automata exhibiting the following (biologically inspired) features: (1) Neurons and synapses evolve in time as in contact with respective baths at different temperatures. (2) The connectivity between neurons may be tuned from full connection to high random dilution or to the case of networks with the small--world property and/or scale-free architecture. (3) There is synaptic kinetics simulating repeated scanning of the stored patterns. Though these features may apparently result in additional disorder, the model exhibits, for a wide range of parameter values, an extraordinary computational performance, and some of the qualitative behaviors observed in natural systems. In particular, we illustrate here very efficient and robust associative memory, and jumping between pattern attractors.