Multiclassifier Systems

Prof. Joydeep Ghosh

University of Texas, USA

http://pegasus.ece.utexas.edu/~ghosh/

Abstract

The theory and practice of using multiple classifiers to solve difficult classification problems is wide regarded as one of the top advancements in pattern recognition over the past decade. This topic includes ensemble approaches such as bagging, boosting, random forests and meta-learners. I will give a broad overview of why and how ensembles work, highlighting key algorithmic techniques as well as theoretical results. Then I will discuss special application scenarios, such as how to deal with a large number of output classes, and how multi-classifiers can be used to tackle a series of related problems through knowledge reuse mechanisms.

Speaker's background:  Joydeep Ghosh was educated at IIT Kanpur (B. Tech '83) and The University of Southern California (MS, Ph.D, '88). Subsequently he joined the the Department of Electrical and Computer Engineering at the University of Texas, Austin, where he is a Full Professor since 1998, and holder of the Archie Straiton Endowed Fellowship. Dr. Ghosh directs the Laboratory for Artificial Neural Systems (LANS), where his research group is studying the theory and applications of adaptive pattern recognition, data mining including web mining, and multi-learner systems.

Dr. Ghosh has published more than 200 refereed papers and edited 10 books. He has received six best paper awards, including the 1992 Darlington Prize for the Best Journal Paper from IEEE Circuits and Systems Society, and the Best Applications Paper at ANNIE'97.

Dr. Ghosh served as Conference Co-Chair of Artificial Neural Networks in Engineering (ANNIE)'93 -ANNIE'96, ANNIE '98-2003, and in the program or organizing committees of several conferences on data mining and neural networks each year. More recently, he co-organized workshops on Web Mining (with SIAM Int'l Conf. on Data Mining, 2001 and 2002) and on Parallel and Distributed Data Mining (with KDD-2000). He was a plenary speaker for ANNIE'97, MCS2002 and letters editor for IEEE Trans.~Neural Networks (1998-2000). He is currently an associate editor of Pattern Recognition, Neural Computing Surveys and Int'l Jl. of Smart Engineering Design.

Back                                                                        Home