Equilibrium propagation reduces forgetting in hopfield continual learning

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

Machine LearningArtificial Intelligence

Summary

Training artificial neural networks to learn new tasks without forgetting old ones is a big challenge known as catastrophic forgetting. The authors study a biologically inspired method called Equilibrium Propagation (EqProp) applied to Hopfield Networks and show how to use the network's own generative abilities to replay memories without storing past data externally. By generating internal pseudo-data representing past tasks, their approach helps the network remember previous knowledge while learning new tasks. They demonstrate improved accuracy on standard image classification tests where tasks are introduced one after another.

What this means in practice

  • For edge device engineers: Build continual learning systems on edge hardware using Hopfield Networks without external memory buffers for past data.
  • For embedded systems developers: Implement low-overhead continual learning for classification tasks in resource-constrained environments by internally generating rehearsal data.

Authors

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

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.