Streaming Continual Learning for Unified Adaptive Intelligence in Dynamic Environments
This work addresses the problem of adaptive intelligence for systems in dynamic environments, but it is incremental as it extends existing frameworks without introducing new methods or results.
The paper tackles the challenge of developing predictive models in dynamic environments by proposing Streaming Continual Learning (SCL), a unified setting that combines Continual Learning and Streaming Machine Learning to adapt to non-stationary data streams without forgetting previous knowledge.
Developing effective predictive models becomes challenging in dynamic environments that continuously produce data and constantly change. Continual Learning (CL) and Streaming Machine Learning (SML) are two research areas that tackle this arduous task. We put forward a unified setting that harnesses the benefits of both CL and SML: their ability to quickly adapt to non-stationary data streams without forgetting previous knowledge. We refer to this setting as Streaming Continual Learning (SCL). SCL does not replace either CL or SML. Instead, it extends the techniques and approaches considered by both fields. We start by briefly describing CL and SML and unifying the languages of the two frameworks. We then present the key features of SCL. We finally highlight the importance of bridging the two communities to advance the field of intelligent systems.