Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability

TL;DR

This paper introduces a sleep-like replay consolidation algorithm for equilibrium propagation-trained RNNs, significantly enhancing their ability to retain knowledge in continual learning scenarios and reducing catastrophic forgetting.

Contribution

It proposes a novel sleep-like replay consolidation method for RNNs trained with equilibrium propagation, improving lifelong learning and knowledge retention.

Findings

SRC improves resilience to catastrophic forgetting.

MRNN-EP with SRC outperforms feedforward networks with regularization.

MRNN-EP with SRC matches BPTT on MNIST and surpasses it on other datasets.

Abstract

Recurrent neural networks (RNNs) trained using Equilibrium Propagation (EP), a biologically plausible training algorithm, have demonstrated strong performance in various tasks such as image classification and reinforcement learning. However, these networks face a critical challenge in continuous learning: catastrophic forgetting, where previously acquired knowledge is overwritten when new tasks are learned. This limitation contrasts with the human brain's ability to retain and integrate both old and new knowledge, aided by processes like memory consolidation during sleep through the replay of learned information. To address this challenge in RNNs, here we propose a sleep-like replay consolidation (SRC) algorithm for EP-trained RNNs. We found that SRC significantly improves RNN's resilience to catastrophic forgetting in continuous learning scenarios. In class-incremental learning with SRC implemented after each new task training, the EP-trained multilayer RNN model (MRNN-EP) performed significantly better compared to feedforward networks incorporating several well-established regularization techniques. The MRNN-EP performed on par with MRNN trained using Backpropagation Through Time (BPTT) when both were equipped with SRC on MNIST data and surpassed BPTT-based models on the Fashion MNIST, Kuzushiji-MNIST, CIFAR10, and ImageNet datasets. Combining SRC with rehearsal, also known as "awake replay", further boosted the network's ability to retain long-term knowledge while continuing to learn new tasks. Our study reveals the applicability of sleep-like replay techniques to RNNs and highlights the potential for integrating human-like learning behaviors into artificial neural networks (ANNs).