Speaker: Shuyuan Yang

Affiliation: Xidian University

Academic title: Professor

Honorary title: National High-Level Talents Special Support Program (Leading Talent of Technological Innovation of Ten-Thousands Talents Program

Abstract:

In complex and uncertain electromagnetic environments, the signal classification is a challenging task for handling "Out-Of-Distribution data" (OOD) that are not from the training distribution. This report discusses some signal classification tasks with open categories, noisy labels and limited instances, and some works on their solution.

Biography:

Shuyuan Yang received the B.Eng., M.Sc. and Ph.D. degrees in electronic engineering, circuit and system from Xidian University, Xi'an, China, in 2000, 2003, and 2005, respectively. Her current research interests include Machine learning, image processing and compressive sensing. She has published seven books and around 100 technical articles in refereed journals and proceedings.