Description
【The 8th Seminar】
Date and Time: February 16th 6:00pm – 7:00pm(JST)
10:00am-11:00pm(CET)
Venue:Zoom webinar
Language: English
Speaker: Qibin Zhao, RIKEN AIP
Title: Efficient Machine Learning with Tensor Networks
Abstract:
Modern ML methods have achieved the remarkable performance by dramatically increasing the DNN model size and the amount of high quality data samples. However, how to learn information from data efficiently and train a parameter efficient model become important in particular applications. Tensor Networks (TNs), which were studied in quantum physics and applied mathematics, have been increasingly investigated and applied to machine learning and signal processing, due to their advantages in handling large-scale and high-dimensional problems, model compression in DNNs, and efficient computations for learning algorithms. This talk aims to present some recent progresses of TNs technology applied to machine learning from perspectives of basic principle and algorithms, particularly in unsupervised learning, data completion, multi-model learning and various applications in deep learning modeling and etc. Finally, we will also present several potential research directions and new trends in this area.
Bio:
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. Then, he joined RIKEN Center for Advanced Intelligence Project as a unit leader (2017 – 2019) and is currently a team leader for tensor learning team. He is also a visiting professor in Tokyo University of Agriculture and Technology and Saitama Institute of Technology, Japan. His research interests include machine learning, tensor factorization and tensor networks, and brain signal processing. He has published more than 150 scientific papers, and co-authored two monographs on tensor networks. He serves as an editorial board member for the journal “Science China: Technological Sciences”, Area Chair for top-tier ML conferences of NeurIPS, ICML, AISTATS, AAAI, IJCAI and ACML. He has (co)-organized several workshops on “tensor networks in machine learning” at NeurIPS 2020, 2021 and IJCAI 2020.
