Abstract:Classical Hopfield networks are limited to static patterns due to symmetric weights, whereas asymmetric networks can encode temporal sequences via limit-cycle attractors. Achieving high-capacity storage of long sequences in classical synchronous asymmetric networks, however, has remained a challenge. We present a simple and robust construction within the classical asymmetric Hopfield model with binary neurons and synchronous updates, that allows $n$ neurons to support $\exp\!\big(\Omega(n/(\log n)^2)\big)$ distinct limit-cycle attractors, each with period $\exp\!\big(\Omega(\sqrt n/\log n)\big)$ and robust to random noise with flip probability up to $\frac12-o(1)$, yielding superpolynomial capacity in both the number and length of stored sequences. This is the first demonstration of such capacity for asymmetric Hopfield networks, which we obtain by combining results from combinatorics, number theory and the analysis of opinion dynamics. Our findings show that synchronous asymmetric Hopfield networks possess a sequence-memory capacity which is larger and more robust than previously recognized, demonstrating that, in both biological and artificial neural systems, robust sequence representation can be achieved through coarse architectural motifs rather than complex nonlinearities.
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.24611 [cs.LG] |
| (or arXiv:2605.24611v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.24611 arXiv-issued DOI via DataCite (pending registration) |
From: Aakash Kumar [view email]
[v1]
Sat, 23 May 2026 14:46:49 UTC (2,659 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。