题目：Tensor Representation for Machine Learning: Efficiency and Reliability

内容简介：Tensor Networks (TNs) are factorizations of high dimensional tensors into networks of many low-dimensional tensors, which have been studied in quantum physics, high-performance computing, and applied mathematics. In recent years, TNs have been increasingly investigated and applied to machine learning and signal processing, due to its significant advances in handling large-scale and high-dimensional problems. This talk aims to present some recent progress of TNs technology developed for machine learning from perspectives of basic principle and algorithms, especially focusing on the efficiency, robustness and interpretability issues in deep learning models.

报告人：Dr. Qibin Zhao

报告人简介：Team Director, Tensor Learning Team RIKEN Center for Advanced Intelligence Project (AIP), Japan.Qibin Zhao received the Ph.D. degree in computer science from Shanghai Jiao Tong University, China in 2009. He was a research scientist at RIKEN Brain Science Institute from 2009 to 2017.  He joined RIKEN Center for Advanced Intelligence Project (AIP) as a unit leader from 2017 to 2019 and is currently a team director for tensor learning team. He is also a visiting professor in Tokyo University of Agriculture and Technology and Guangdong University of Technology. His research interests include machine learning, tensor factorization and tensor networks, computer vision and brain signal processing. He has published more than 250 scientific papers in international journals and conferences and two monographs on tensor networks. He serves as an Action Editor for “Neural Networks”, as well as Area Chair for the major ML conference of NeurIPS, ICML, ICLR.

时间：2025年12月23日（周二）16:00开始

地点：石牌校区南海楼407会议室

热烈欢迎广大师生参加!

信息科学技术学院

2025年12月23日