Continual Deep Learning by Functional Regularisation of Memorable Past

TL;DR

This paper introduces a novel functional regularisation method for continual deep learning that leverages memorable past examples and Gaussian Process formulation to prevent catastrophic forgetting, achieving state-of-the-art results.

Contribution

It proposes a new functional regularisation approach using memorable past examples and Gaussian Processes, improving continual learning performance.

Findings

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

Effectively prevents catastrophic forgetting in continual learning.

Combines regularisation and memory-based methods seamlessly.

Abstract

Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past. Recent works address this with weight regularisation. Functional regularisation, although computationally expensive, is expected to perform better, but rarely does so in practice. In this paper, we fix this issue by using a new functional-regularisation approach that utilises a few memorable past examples crucial to avoid forgetting. By using a Gaussian Process formulation of deep networks, our approach enables training in weight-space while identifying both the memorable past and a functional prior. Our method achieves state-of-the-art performance on standard benchmarks and opens a new direction for life-long learning where regularisation and memory-based methods are naturally combined.