RECAP: Local Hebbian Prototype Learning as a Self-Organizing Readout for Reservoir Dynamics

TL;DR

RECAP introduces a bio-inspired, local learning approach combining reservoir dynamics with Hebbian prototypes for robust image classification, avoiding backpropagation and enabling online updates, demonstrated on MNIST-C.

Contribution

It proposes a novel self-organizing Hebbian prototype readout for reservoir computing, aligning with biological principles and improving robustness without error backpropagation.

Findings

RECAP maintains robustness under diverse corruptions on MNIST-C.

The method avoids error backpropagation, enabling online learning.

It effectively classifies images using reservoir dynamics and Hebbian prototypes.

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.