Jacek M. Zurada University of Louisville, Louisville, Kentucky, USA 2014 IEEE VP-Technical Activities (2013-Elect) Keynote title : Nonnegative Matrix Factorization and Its Application to Pattern Analysis and Text Mining

Abstract:

Nonnegative Matrix Factorization (NMF) is one of the most promising techniques to reduce the number of attributes of the data. This presentation compares the method with other popular matrix decomposition approaches for various pattern analysis tasks. Among others, NMF has been also widely applied for clustering and latent feature extraction. Several types of the objective functions have been used for NMF in the literature.  Instead of minimizing the common Euclidean Distance (EucD) error, we review an alternative method that maximizes the correntropy similarity measure to produce the factorization. Correntropy is an entropy-based criterion defined as a nonlinear similarity measure. Following the discussion of maximization of the correntropy function, we use it to cluster document data set and compare the clustering performance with the EucD-based NMF. Our approach was applied and illustrated for the clustering of documents in the 20-Newsgroups data set. The results show that our approach produces per average better clustering compared with other methods which use EucD as an objective function.

Short Bio:

Jacek M. Zurada (FIEEE) serves as a University Scholar and Professor with the Electrical and Computer Engineering Department at the University of Louisville, Kentucky. He was Department Chair from 2004 to 2006. He has published 360 journal and conference papers in the areas of neural networks, computational intelligence, data mining, image processing and VLSI circuits. He also has authored or co-authored three books and co-edited a number of volumes in Springer Lecture Notes on Computer Science. His work received over 6500 citations by other authors.

He has held visiting appointments at Princeton, Northeastern, Auburn, and overseas in Australia, Chile, China, France, Germany, Hong Kong, Italy, Japan, Poland, Singapore, Spain, South Africa and Taiwan. Dr. Zurada was an Associate Editor of IEEE Transactions on Circuits and Systems, Pt. I and Pt. II, and served on the Editorial Board of the Proceedings of IEEE. From 1998 to 2003 he was the Editor-in-Chief of IEEE Transactions on Neural Networks. He is an Associate Editor of Neurocomputing, Schedae Informaticae, International Journal of Applied Mathematics and Computer Science, Advisory Editor of Int’l Journal of Information Technology and Intelligent Computing, and Editor of Springer Natural Computing Book Series. 

He has served the profession and the IEEE in various capacities. He was elected as 2014 IEEE VP-Technical Activities (2013-Elect). He was President of IEEE Computational Intelligence Society in 2004-05 and the ADCOM member in 2009-14 and earlier years. He now chairs the IEEE TAB Periodicals Review and Advisory Committee and chaired the IEEE TAB Periodicals Committee in 2010-11.  In 2011 he was Vice-Chair of PSPB and member of PSPB Strategic Planning Committee (2010-11)

Dr. Zurada has received a number of awards for distinction in research, teaching, and service including the 1993 Presidential Award for Research, Scholarship and Creative Activity, 1999 IEEE Circuits and Systems Society Golden Jubilee Medal, and the 2001 Presidential Distinguished Service Award for Service to the Profession. He is a Distinguished Speaker of IEEE CIS. In 2003 he was conferred the Title of National Professor by the President of Poland. He received four Honorary Professorships from Chinese universities. Since 2005 he has been a Member of the Polish Academy of Sciences, and was appointed as a Senior Fulbright Specialist for 2006-12.