Title: On Tensor Networks and Neural Networks
Speaker: Zenglin Xu
Affiliation: Statistical Machine Intelligence & LEarning (SMILE) Lab, University of Electronic Science & Technology (UESTC), Chengdu, Sichuan, China
Time: 11:00am-12:00am, 25th May,2018
Address:Communication Building 818 Conference Room, Shahe Campus, UESTC.
Zenglin Xu is a Professor in School of Computer Science and Engineering at University of Electronic Science and Technology of China(UESTC). He is the founder and director of the Statistical Machine Intelligence and LEarning (SMILE) Lab. He is a recipient of China Thousand Talents(Youth) Program. He obtained his PhD in Computer Science and Engineering from the Chinese University of Hong Kong. His research interest includes machine learning and its applications on social network analysis, health informatics, and cyber security analytics. He has published over 70 papers in prestigious journals and conferences such as NIPS, ICML, IJCAI, AAAI, IEEE PAMI, IEEE TNN, etc. He is also the recipient of the APNNS young researcher award, and the best student paper honorable mention of AAAI 2015. Dr. Xu has been a PC member or reviewer to a number of top conferences such as NIPS, ICML, AAAI, IJCAI, etc. He regularly servers as a reviewer to IEEE TPAMI, JMLR, PR, IEEE TNN, IEEE TKDD, ACM TKDD, etc.
In the big data era, multiway data are almost everywhere, e.g., recommendation systems, face recognition, sensor networks, etc. Tensor factorization is an important approach to multiway data analysis. The speaker will first briefly introduce canonical methods as well as recent developments of tensor factorization. Then, the speaker will discuss the connections between tensor networks and deep neural networks, and especially how to compress deep neural networks with tensor networks.