Logo image
Retour
Generative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks
Document de travail   Open Access

Generative Replay for Equilibrium Propagation: Toward Edge-Friendly Continual Learning in Hopfield Networks

Victor Cook, Gilles Sassatelli, Marina Reyboz, Thierry Gil et Mohamed Watfa

Résumé

Dynamic Neural Networks Efficient and Tiny Neural Networks Physics-Inspired Neural Networks and Neural Operators Continual Learning
Continual learning at the edge requires models that can adapt to non-stationary data streams under strict memory and energy constraints. While Equilibrium Propagation (EqProp) in Hopfield Networks offers a biologically grounded and hardware-aligned alternative to backpropagation, its behavior in continual learning settings remains largely unexplored. In particular, standard ER relies on stored samples, which conflicts with analog and neuromorphic implementations where external memory is costly or unavailable.

This work addresses the problem of catastrophic forgetting in EqProp-trained Hopfield Networks without relying on data buffers or architectural additions. We introduce an Energy-Based Generative Replay strategy (EB-GenReplay) that exploits the intrinsic generative dynamics of Hopfield Networks, allowing a single model to act as both classifier and replay generator. Past task samples are regenerated by relaxing a frozen copy of the network, enabling rehearsal through internally generated pseudodata.

We evaluate the proposed method on the Split-MNIST benchmark and compare it against FineTune and Experience Replay (ER). The results show that EB-GenReplay significantly improves stability while preserving plasticity, achieving competitive average accuracy (76% for EB-GenReplay vs. 85% for ER) without the need for external memory. These findings position EqProptrained Hopfield Networks as a compact and edge-friendly foundation for continual learning.

Fichiers et liens (1)

url
Find in HALAfficher

Indicateurs

1 Consultations de la notice

Détails

Logo image