42 citations · 45 across the 4 of their papers we have counts for
4 papers · 1 filter
Towards Continuous Power Forecasting: Practical Continual Learning for Real-World Energy Systems in Nonstationary Time Series
Yujiang He, Frederic Uhrweiller, Bernhard Sick
Power forecasting models deployed in real-world energy markets must operate under nonstationary conditions, where data distributions continually evolve due to weather variability,…
Spatio-Temporal Attention Graph Neural Network for Remaining Useful Life Prediction
Zhixin Huang, Yujiang He, Bernhard Sick
Remaining useful life prediction plays a crucial role in the health management of industrial systems. Given the increasing complexity of systems, data-driven predictive models have…
Design of Explainability Module with Experts in the Loop for Visualization and Dynamic Adjustment of Continual Learning
Yujiang He, Zhixin Huang, Bernhard Sick
Continual learning can enable neural networks to evolve by learning new tasks sequentially in task-changing scenarios. However, two general and related challenges should be overcom…
CLeaR: An Adaptive Continual Learning Framework for Regression Tasks
Yujiang He, Bernhard Sick
Catastrophic forgetting means that a trained neural network model gradually forgets the previously learned tasks when being retrained on new tasks. Overcoming the forgetting proble…