arXiv cs.AI· Victor Cook (LIRMM | ADAC), Gilles Sassatelli (LIRMM | ADAC), Thierry Gil (LIRMM), Mohamed Watfa (LIRMM | ADAC), Marina Reyboz (CEA-LETI)·· 3 小时前AI 评分32
面向边缘友好的持续学习：Hopfield 网络中 EqProp 的能量生成式回放（EB-Gen）方法
Generative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks
AI 导读
一项 arXiv 研究提出能量生成式回放策略 EB-Gen，利用 Hopfield 网络的内在生成动态，让单一模型同时充当分类器和回放样本生成器，缓解 Equilibrium Propagation 训练中的灾难性遗忘，无需外部数据缓冲或额外架构开销。
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