What are Classifier Ensembles Good for Anyway and How Would You Know?¶
Lawrence O. Hall
Professor
University of South Florida
Abstract :
Ensembles of classifiers can result in an overall classifier with more
predictive accuracy than a single classifier. However, they are more costly
to create. In this talk we will argue that an ensemble can be useful in
building a model of very large data sets even if members of the ensemble are
trained on only a non-stratified portion of the data. Several examples will
be given. Further, a 57 data set statistical comparison of some rapid, and
not so rapid, ensemble classifier construction approaches will be discussed
to examine where a classifier ensemble is beneficial and what type may be
most likely to provide the highest accuracy.
Bio:
Lawrence O. Hall is Professor and Chair of Computer Science and Engineering
at University of South Florida. He received his Ph.D. in Computer Science
from the Florida State University in 1986 and a B.S. in Applied Mathematics
from the Florida Institute of Technology in 1980. He is a fellow of the IEEE
and the IAPR. His research interests lie in distributed machine learning,
extreme data mining, pattern recognition and integrating AI into image
processing. The exploitation of imprecision with the use of fuzzy logic in
pattern recognition, AI and learning is a research theme. He has authored or
co-authored over 65 publications in journals, as well as many conference
papers and book chapters. Some recent publications appear in IEEE
Transactions on Pattern Analysis and Machine Intelligence, Neural
Computation, Pattern Recognition Letters, Journal of Machine Learning
research, IEEE Transactions on Systems, Man, and Cybernetics, IEEE
Transactions on Evolutionary Computing, the International Conference on Data
Mining, the Multiple Classier Systems Workshop, and the NAFIPS conference.
He received the IEEE SMC Society Outstanding contribution award in 2000 and
2008. He received an Outstanding Research achievement award from the Univ.
of South Florida in 2004. He is a past president of NAFIPS. Larry is the
former vice president for membership of the SMC society. He was the
President of the IEEE Systems, Man and Cybernetics society for 2006-7. He
was the Editor-In-Chief of the IEEE Transactions on Systems, Man and
Cybernetics, Part B, 2002-05. He was the Vice President for Publications for
the IEEE Biometrics Council 2008-10. Also, associate editor for IEEE
Transactions on Fuzzy Systems, International Journal of Intelligent Data
Analysis, International Journal of Pattern Recognition and Artificial
Intelligence and International Journal of Approximate Reasoning.