Title

A Theoretical and Empirical Study of a Noise-Tolerant Algorithm to Learn Geometric Patterns

Authors

Sally A. Goldman, Washington University in St Louis
Stephen D. Scott, Washington University in St. Louis

Document Type

Technical Report

Department

Computer Science and Engineering

Publication Date

1997-01-01

Filename

WUCS-97-20.PDF

DOI:

10.7936/K7B856BZ

Technical Report Number

WUCS-97-20

Abstract

Developing the ability to recognize a landmark from a visual image of a robot's current location is a fundamental problem in robotics. We describe a way in which the landmark matching problem can be mapped to that of learning a one-dimensional geometric pattern. The first contribution of our work is an efficient noise-tolerant algorithm (designed using the statistical query model) to PAC-learn the class of one-dimensional geometric patterns. The second contribution of our work is an empirical study of our algorithm that provides at least some evidence that statistical query algorithms may be valuable for use in practice for handling noisy data.

Comments

Permanent URL: http://dx.doi.org/10.7936/K7B856BZ

Recommended Citation

Goldman, Sally A. and Scott, Stephen D., "A Theoretical and Empirical Study of a Noise-Tolerant Algorithm to Learn Geometric Patterns" Report Number: WUCS-97-20 (1997). All Computer Science and Engineering Research.
https://openscholarship.wustl.edu/cse_research/436