Title: Data Visualization by Neighbor Embedding

Abstract: Modern data analysis is not only massive but also complex in terms of various structural information. Visual representations and interaction techniques take advantage of the human eye's broad bandwidth pathway into the mind to allow users to see, explore, and understand large amounts of information in an efficient way. Therefore, data visualization is an important tool and a crucial middle step in machine learning, data mining and analysis. In this talk I will present a new family of data visualization methods called Neighbor Embedding. In particular, the talk will focus on the use of  various information divergences and embedding kernels, as well as the development of their scalable optimization algorithms.

Bio: Zhirong Yang received his Doctoral degree from Helsinki University of Technology, Finland in 2008. Presently he is a Docent (Adjunt professor) in the Department of Information and Computer Science at Aalto University. He is also a postdoctoral researcher at The Finnish Centre of Excellence in Computational Inference Research (COIN). He is now focus on on data visualization and other manifold learning research. He is also interested in other machine learning and pattern recognition problems, especially nonnegative matrix factorization, cluster analysis, and learning representations.