Portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 1
Short description of portfolio item number 2 
Published in IEEE International Conference on Data Mining (ICDM), 2025
We demonstrate that spectral bias—the tendency of neural networks to fit low-frequency signals first—is a universal trait in time-series prediction, not an architectural artifact. To mitigate this, we propose FreLE, an algorithm using frequency regularization to improve model generalization. Extensive experiments confirm FreLE’s effectiveness.
发布时间:
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.