arXiv cs.AI· Victor Cook (LIRMM | ADAC), Gilles Sassatelli (LIRMM | ADAC), Thierry Gil (LIRMM), Mohamed Watfa (LIRMM | ADAC), Marina Reyboz (CEA-LETI)·· 13 小时前AI 评分18
基于能量生成回放的 Equilibrium Propagation：面向 Hopfield 网络的边缘友好持续学习
Generative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks
AI 导读
研究提出 Energy-Based Generative Replay（EB-Gen）策略，利用 Hopfield 网络自身的生成动力学，让单一模型同时充当分类器与回放样本生成器，无需外部数据缓冲或额外架构。在 Split MNIST 和 Split CIFAR10 的类增量设置中，该方法平均准确率分别达 75% 和 64%，在保持可塑性的同时显著提升稳定性。
正文 · 原文
Abstract:Equilibrium Propagation (EqProp) offers a biologically grounded and hardware-aligned alternative to backpropagation for training Hopfield Networks. However, its behavior in continual learning settings remains largely unexplored. This work confronts catastrophic forgetting in EqProp-trained Hopfield Networks from the inside out, eliminating the need for external data buffers or architectural overhead that standard Experience Replay \textbf{(ER)} and Generative Replay \textbf{(Gen-Replay)} inevitably require. We introduce an Energy-Based Generative Replay strategy \textbf{(EB-Gen)} which exploits the intrinsic generative dynamics of Hopfield Networks, allowing a single model to act as both classifier and replay samples generator. Samples capturing past task knowledge are generated by relaxing a frozen copy of the network, enabling rehearsal solely through internally generated pseudo-data. We evaluate the proposed method in the Class-Incremental setting, using the split versions of the MNIST and CIFAR10 benchmarks and compare it with FineTune, Experience Replay, Generative Replay, Sleep-Like Replay Consolidation (SRC) and Joint training. Our results show that EB-Gen significantly improves stability while preserving plasticity, achieving a 75\% and 64\% average accuracy on Split MNIST and Split CIFAR10 respectively. These findings show that Equilibrium Propagation can be adapted to alleviate catastrophic forgetting without forgoing the traits which made it compelling in the first place.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.37139 [cs.LG] |
| (or arXiv:2610.37139v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37139 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Victor Cook [view email] [via CCSD proxy]
[v1]
Tue, 27 Oct 2026 12:35:20 UTC (238 KB)
来源：arXiv cs.AI · arxiv.org