Amorphous Solid Model of Vectorial Hopfield Neural Networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gallavotti, F., Zaccone, A.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915663108374528
author Gallavotti, F.
Zaccone, A.
author_facet Gallavotti, F.
Zaccone, A.
contents 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 $γ_c$ grows approximately linearly with the coordination number $Z$, while for $Z\gtrsim 40$ a high-connectivity regime emerges in which $γ_c$ 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_22787
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Amorphous Solid Model of Vectorial Hopfield Neural Networks
Gallavotti, F.
Zaccone, A.
Disordered Systems and Neural Networks
Soft Condensed Matter
Statistical Mechanics
Machine Learning
Neural and Evolutionary Computing
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 $γ_c$ grows approximately linearly with the coordination number $Z$, while for $Z\gtrsim 40$ a high-connectivity regime emerges in which $γ_c$ 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.
title Amorphous Solid Model of Vectorial Hopfield Neural Networks
topic Disordered Systems and Neural Networks
Soft Condensed Matter
Statistical Mechanics
Machine Learning
Neural and Evolutionary Computing
url https://arxiv.org/abs/2507.22787