Noise-tolerant parallel learning of geometric concepts

DOI10.1006/inco.1998.2737zbMath0927.68118OpenAlexW2042050521MaRDI QIDQ1281499

H. David Mathias, Nader H. Bshouty, Sally A. Goldman

Publication date: 29 November 1999

Published in: Information and Computation (Search for Journal in Brave)

Full work available at URL: https://openscholarship.wustl.edu/cgi/viewcontent.cgi?article=1434&context=cse_research

zbMATH Keywords

parallel algorithmsPAC-learning

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Parallel algorithms in computer science (68W10)

Related Items (2)

Intrinsic complexity of learning geometrical concepts from positive data ⋮ Cryptographic limitations on parallelizing membership and equivalence queries with applications to random-self-reductions

Cites Work

• Unnamed Item
• Unnamed Item
• On learning a union of half spaces
• Equivalence of models for polynomial learnability
• Learning in parallel
• Lower bound methods and separation results for on-line learning models
• Composite geometric concepts and polynomial predictability
• A general lower bound on the number of examples needed for learning
• The bounded injury priority method and the learnability of unions of rectangles
• Learning from a consistently ignorant teacher
• Queries and concept learning
• Learnability and the Vapnik-Chervonenkis dimension
• A theory of the learnable
• Efficient noise-tolerant learning from statistical queries
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

This page was built for publication: Noise-tolerant parallel learning of geometric concepts