Continual Learning With Speculative Backpropagation and Activation History

Abstract

Continual learning is gaining traction these days with the explosive emergence of deep learning applications. Continual learning suffers from a severe problem called catastrophic forgetting. It means that the trained model loses the previously learned information when training with new data. This paper proposes two novel ideas for mitigating catastrophic forgetting: Speculative Backpropagation (SB) and Activation History (AH). The SB enables performing backpropagation based on past knowledge. The AH enables isolating important weights for the previous task. We evaluated the performance of our scheme in terms of accuracy and training time. The experiment results show a 4.4% improvement in knowledge preservation and a 31% reduction in training time, compared to the state-of-the-arts (EWC and SI).

Keywords

• Continual learning
• lifelong learning
• catastrophic forgetting
• parallel training
• speculative backpropagation
• activation history