Learning on Manifolds and Big Data Applications
The geometry of a given space characterizes the proximity between data and plays a key role in machine learning. The traditional methods of simply and naively treating data spaces as "flat" Euclidean’s may not offer desired effect in variety of learning tasks. In this talk, I would like to report some of my recent research on learning tasks over manifolds and try to give an introduction to the state-of-the-art learning on manifolds. The focus will be on the low-rank representation (LRR) models on the Grassmann manifold and the curves manifold used in learning tasks from computer vision.
Biography of the Speaker:
Professor Junbin Gao is a Professor of Big Data Analytics in the University of Sydney Business School. Prior to this appointment, he was a Professor in Computing Science in the School of Computing and Mathematics and the deputy Director of Centre for Research in Complex Systems (CRiCS) at Charles Sturt University. He was a senior lecturer, a lecturer in Computer Science from 2001 to 2005 at University of New England. From 1982 to 2001 he was an associate lecturer, lecturer, associate professor and professor in Department of Mathematics at Huazhong University of Science and Technology. Professor Gao graduated from Huazhong University of Science and Technology (HUST), China in 1982 with a B.Sc. degree in Computational Mathematics and obtained his PhD from Dalian University of Technology, China in 1991. His main research interests include machine learning, data mining, Bayesian learning and inference, and image analysis. His research is supported by two ARC DP grants and two larger industrial grants. He has published more than 220 research papers including 69 ERA A*/A journal articles and conference papers. He was the recipient of the 2014 CSU VC's Awards for Excellence in Research.