Online Continual Learning for Time-Series Forecasting

Title	Online Continual Learning for Time-Series Forecasting
Summary	This project explores online continual learning to train models that adapt to changing environments and new tasks while retaining previously learned knowledge.
Keywords	Online Continual Learning; Time-series Forecasting; concept driftProperty "Keywords" has a restricted application area and cannot be used as annotation property by a user.
TimeFrame
References
Prerequisites
Author
Supervisor	Nuwan Gunasekara, Yuantao Fan
Level
Status	Ongoing

This project explores how online continual learning methods can be designed and employed for time-series forecasting so that models can be adapted rapidly to evolving environments and new tasks without catastrophic forgetting.