A theoretical and empirical study of a noise-tolerant algorithm to learn geometric patterns

DOI10.1023/A:1007681724516zbMath0949.68534OpenAlexW2037094344MaRDI QIDQ1961321

Sally A. Goldman, Stephen D. Scott

Publication date: 17 January 2000

Published in: Machine Learning (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1023/a:1007681724516

zbMATH Keywords

roboticsstatistical query modelnoise-tolerant PAC learning

Mathematics Subject Classification ID

Computational learning theory (68Q32) Artificial intelligence for robotics (68T40)

Related Items (2)

Intrinsic complexity of learning geometrical concepts from positive data ⋮ Agnostic learning of geometric patterns

This page was built for publication: A theoretical and empirical study of a noise-tolerant algorithm to learn geometric patterns