Latent Space based Memory Replay for Continual Learning in Artificial Neural Networks

TL;DR

This paper proposes a latent space based memory replay method for artificial neural networks to mitigate catastrophic forgetting in continual learning, by storing compressed representations of previous data.

Contribution

It introduces a novel approach of using compressed latent space representations for memory replay to improve continual learning in neural networks.

Findings

Preserves performance on previous tasks effectively.

Stores only a small percentage of data in latent space.

Reduces catastrophic forgetting in neural networks.

Abstract

Memory replay may be key to learning in biological brains, which manage to learn new tasks continually without catastrophically interfering with previous knowledge. On the other hand, artificial neural networks suffer from catastrophic forgetting and tend to only perform well on tasks that they were recently trained on. In this work we explore the application of latent space based memory replay for classification using artificial neural networks. We are able to preserve good performance in previous tasks by storing only a small percentage of the original data in a compressed latent space version.