Continual Learning in Human Activity Recognition: an Empirical Analysis of Regularization
This work addresses the need for continual learning methods that generalize across diverse domains, such as HAR, but is incremental as it analyzes existing techniques rather than proposing new ones.
The paper tackled the problem of applying continual learning techniques from computer vision to human activity recognition (HAR), finding that most regularization approaches lack substantial effect and providing insights into their failures.
Given the growing trend of continual learning techniques for deep neural networks focusing on the domain of computer vision, there is a need to identify which of these generalizes well to other tasks such as human activity recognition (HAR). As recent methods have mostly been composed of loss regularization terms and memory replay, we provide a constituent-wise analysis of some prominent task-incremental learning techniques employing these on HAR datasets. We find that most regularization approaches lack substantial effect and provide an intuition of when they fail. Thus, we make the case that the development of continual learning algorithms should be motivated by rather diverse task domains.