Learning Fast, Learning Slow: A General Continual Learning Method based on Complementary Learning System

TL;DR

This paper introduces CLS-ER, a dual memory experience replay method inspired by brain's complementary learning system, enabling neural networks to learn continually without task boundaries and reducing catastrophic forgetting.

Contribution

It presents a novel dual memory replay approach that integrates short-term and long-term memories for improved general continual learning.

Findings

Achieves state-of-the-art results on standard benchmarks.

Performs well in realistic, task-free continual learning scenarios.

Does not rely on task boundaries or data distribution assumptions.

Abstract

Humans excel at continually learning from an ever-changing environment whereas it remains a challenge for deep neural networks which exhibit catastrophic forgetting. The complementary learning system (CLS) theory suggests that the interplay between rapid instance-based learning and slow structured learning in the brain is crucial for accumulating and retaining knowledge. Here, we propose CLS-ER, a novel dual memory experience replay (ER) method which maintains short-term and long-term semantic memories that interact with the episodic memory. Our method employs an effective replay mechanism whereby new knowledge is acquired while aligning the decision boundaries with the semantic memories. CLS-ER does not utilize the task boundaries or make any assumption about the distribution of the data which makes it versatile and suited for "general continual learning". Our approach achieves state-of-the-art performance on standard benchmarks as well as more realistic general continual learning settings.