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

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 some evidence that statistical query algorithms may be valuable for use in practice for handling noisy data.

Cite

Text

Goldman and Scott. "A Theoretical and Empirical Study of a Noise-Tolerant Algorithm to Learn Geometric Patterns." Machine Learning, 1999. doi:10.1023/A:1007681724516

Markdown

[Goldman and Scott. "A Theoretical and Empirical Study of a Noise-Tolerant Algorithm to Learn Geometric Patterns." Machine Learning, 1999.](https://mlanthology.org/mlj/1999/goldman1999mlj-theoretical/) doi:10.1023/A:1007681724516

BibTeX

@article{goldman1999mlj-theoretical,
  title     = {{A Theoretical and Empirical Study of a Noise-Tolerant Algorithm to Learn Geometric Patterns}},
  author    = {Goldman, Sally A. and Scott, Stephen D.},
  journal   = {Machine Learning},
  year      = {1999},
  pages     = {5-49},
  doi       = {10.1023/A:1007681724516},
  volume    = {37},
  url       = {https://mlanthology.org/mlj/1999/goldman1999mlj-theoretical/}
}