Search Results for author:
Found 3 papers, 3 papers with code
Mixup Domain Adaptations for Dynamic Remaining Useful Life Predictions
MDAN encompasses a three-staged mechanism where the mix-up strategy is not only performed to regularize the source and target domains but also applied to establish an intermediate mix-up domain where the source and target domains are aligned.
Dynamic Long-Term Time-Series Forecasting via Meta Transformer Networks
A slow learner tailors suitable representations to fast learners.
Few-Shot Continual Learning via Flat-to-Wide Approaches
This paper proposes a few-shot continual learning approach, termed FLat-tO-WidE AppRoach (FLOWER), where a flat-to-wide learning process finding the flat-wide minima is proposed to address the catastrophic forgetting problem.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
