Accession Number : ADA328730

Title :   Extending and Unifying Formal Models for Machine Learning

Descriptive Note : Final rept. 1 Aug 92-31 Jul 95

Corporate Author : PRINCETON UNIV NJ DEPT OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCE

Personal Author(s) : Kulkarni, Sanjeev R.

PDF Url : ADA328730

Report Date : 30 JUL 1997

Pagination or Media Count : 8

Abstract : There has been a great deal of work on statistical pattern recognition, non-parametric estimation, and formal models of machine learning. Recent and classical work in these areas have provided fundamental results on the amount of data needed for classification, estimation, and prediction in a variety of non-parametric settings. The applicability of these paradigms is often limited by the assumptions on the data gathering mechanisms and the performance criteria. Our work has had two primary goals. The first is to investigate extensions and new models which give results useful in broader applications. The second goal is to apply these learning results to other areas such as signal/image processing, geometric reconstruction, and system identification. We have studied a variety of problems and have been able to relax assumptions required on the observed data as well as on the success criteria while still obtaining positive results. Our results have provided new insights into classical work and have also suggested a number of directions for further work.

Descriptors :   *LEARNING MACHINES, *PATTERN RECOGNITION, *ARTIFICIAL INTELLIGENCE, ALGORITHMS, SIGNAL PROCESSING, IMAGE PROCESSING, STOCHASTIC PROCESSES, NONPARAMETRIC STATISTICS, APPROXIMATION(MATHEMATICS), HYBRID SYSTEMS.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE