RECAP：以局部 Hebbian 原型学习作为储备池动力学的自组织读出
RECAP: Local Hebbian Prototype Learning as a Self-Organizing Readout for Reservoir Dynamics
AI 导读
研究者提出 RECAP（Reservoir Computing with Hebbian Co-Activation Protocols，一种受生物启发的学习策略），将未经训练的储备池动力学与自组织 Hebbian 原型读出相结合，用于鲁棒图像分类。
正文 · 原文
Abstract:Robust perception in brains is often attributed to high-dimensional population activity together with local plasticity mechanisms that reinforce recurring structure. In contrast, most modern image recognition systems are trained by error backpropagation and end-to-end gradient optimization, which are not naturally aligned with local computation and local plasticity. We introduce RECAP (Reservoir Computing with Hebbian Co-Activation Prototypes), a bio-inspired learning strategy for robust image classification that couples untrained reservoir dynamics with a self-organizing Hebbian prototype readout. RECAP discretizes time-averaged reservoir responses into activation levels, constructs a co-activation mask over reservoir unit pairs, and incrementally updates class-wise prototype matrices via a Hebbian-like potentiation-decay rule. Inference is performed by overlap-based prototype matching. The method avoids error backpropagation and is naturally compatible with online prototype updates. We illustrate the resulting robustness behavior on MNIST-C, where RECAP remains robust under diverse corruptions without exposure to corrupted training samples.
| Comments: | Accepted at AICCC 2026. 14 pages, 6 figures |
| Subjects: | Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC) |
| Cite as: | arXiv:2603.06639 [cs.NE] |
| (or arXiv:2603.06639v2 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2603.06639 arXiv-issued DOI via DataCite |
Submission history
From: Heng Zhang [view email]
[v1]
Wed, 25 Feb 2026 08:28:35 UTC (6,854 KB)
[v2]
Tue, 10 Nov 2026 01:58:09 UTC (6,740 KB)
来源：arXiv cs.AI · arxiv.org