Tom Bylander is an Associate Professor of Computer Science at the University of Texas at San Antonio. He received his B.S. in Mathematics and Computer Science from the University of South Dakota in 1979, and his Masters and Ph.D. in Computer and Information Science from the Ohio State University in 1980 and 1986, respectively. He was a faculty member at Ohio State from 1986 to 1993 before coming to UTSA.
His research in artificial intelligence is concerned with the study of efficient algorithms for planning and machine learning and with applications of artificial intelligence to medical domains. Look at some of his publications for examples.
His main focus has been on the analysis, design, and testing of machine learning algorithms. His analysis work has focused on the analysis of linear learning algorithms, in particular, the behavior of the perceptron update rule in the presence of noise. The analyses have led to the design of more sophisticated percepton learning algorithms for noisy examples. Currently, he is still working on machine learning algorithms for noisy data.
Tom Bylander's Home Page