Amorphous Solid Model of Vectorial Hopfield Neural Networks

TL;DR

This paper introduces a vectorial extension of the Hopfield neural network model inspired by amorphous solids, demonstrating improved storage capacity and robustness through spectral analysis and simulations.

Contribution

It presents a novel vectorial Hopfield model with amorphous-solid-inspired structure, outperforming classical models in storage and retrieval capabilities.

Findings

Substantially higher storage capacity than classical Hopfield networks.

Spectral gap separates pattern modes from noise, enhancing robustness.

High connectivity regimes further improve memory performance.

Abstract

We introduce a three-dimensional vectorial extension of the Hopfield associative-memory model in which each neuron is a unit vector on $S^2$ and synaptic couplings are $3\times 3$ blocks generated through a vectorial Hebbian rule. The resulting block-structured operator is mathematically analogous to the Hessian of amorphous solids and induces a rigid energy landscape with deep minima for stored patterns. Simulations and spectral analysis show that the vectorial network substantially outperforms the classical binary Hopfield model. For moderate connectivity, the critical storage ratio $\gamma_c$ grows approximately linearly with the coordination number $Z$, while for $Z\gtrsim 40$ a high-connectivity regime emerges in which $\gamma_c$ systematically exceeds the extrapolated low-$Z$ linear fit. At the same time, a persistent spectral gap separates pattern modes from the bulk and basins of attraction enlarge, yielding enhanced robustness to initialization noise. Thus geometric constraints combined with amorphous-solid-inspired structure produce associative memories with superior storage and retrieval performance, especially in the high-connectivity ($Z \gtrsim 20$-$30$) regime.