Maximal width learning of binary functions

DOI10.1016/j.tcs.2009.09.020zbMath1189.68173OpenAlexW2131319366MaRDI QIDQ1041230

Joel Ratsaby, Martin Anthony

Publication date: 1 December 2009

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2009.09.020

zbMATH Keywords

learning algorithmsbinary function classes

Mathematics Subject Classification ID

Nonnumerical algorithms (68W05) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (9)

Large width nearest prototype classification on general distance spaces ⋮ Classification based on prototypes with spheres of influence ⋮ Robust cutpoints in the logical analysis of numerical data ⋮ Learning bounds via sample width for classifiers on finite metric spaces ⋮ A hybrid classifier based on boxes and nearest neighbors ⋮ Constrained versions of Sauer's Lemma ⋮ Multi-category classifiers and sample width ⋮ On the complexity of binary samples ⋮ A probabilistic approach to case-based inference

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Sharper bounds for Gaussian and empirical processes
• Efficient distribution-free learning of probabilistic concepts
• Learnability and the Vapnik-Chervonenkis dimension
• Covering numbers for real-valued function classes
• Scale-sensitive dimensions, uniform convergence, and learnability
• The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network
• Function Learning from Interpolation
• Neural Network Learning
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities

This page was built for publication: Maximal width learning of binary functions