Machine learning introduction and selected progress on high dimension low sample size imbalance classification

2018-06-06

 Topic Machine learning introduction and selected progress on high dimension low sample size imbalance classification

SpeakerLingsong  Zhang (Purdue University, Associate Professor)

Time 9:30-11:30 June 82018

SiteEMS B251

Abstract:  In the talk, we will give a general introduction to machine learning, with emphasis on supervised machine learning. Some popular methods and its implementation on big data will be discussed. Specially we will introduce support vector machine, its nice properties and some drawbacks when applying it to high dimension low sample size and imbalance data. Such data is widely available in observational studies. An improved classifier will be introduced. We will show the improvement both in theory and by using simulation examples. Application of such approach to a call center data will be provided as well.

Introduction to the Speaker: Dr. Zhang is an associate professor in Department of Statistics, Purdue University. He got his PHD degree in Statistics from University of North Carolina at Chapel Hill, Master degree from Tsinghua University, Bachelor degree from Peking University. His research interests include: Machine Learning and Big data analysis, High Dimensional Inference, Functional and Object Oriented Data Analysis, Data Visualization, and Scale Space Inference.