Compactness Hypothesis, Potential Functions, and Rectifying Linear Space in Machine Learning

DOI10.1007/978-3-319-99492-5_3zbMATH Open1518.68316OpenAlexW2888421493MaRDI QIDQ6104512FDOQ6104512

Authors: Vadim Mottl, Oleg Seredin, Olga Krasotkina 

Publication date: 28 June 2023

Published in: Braverman Readings in Machine Learning. Key Ideas from Inception to Current State (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-3-319-99492-5_3

Recommendations

• scientific article; zbMATH DE number 53984
• Institute of control sciences through the lens of VC dimension
• On the Concept of Compositional Complexity
• Statistical learning theory: A primer
• Three fundamental concepts of the capacity of learning machines

zbMATH Keywords

ordinal regressionpattern recognitionpotential functiondistance transformationregularized empirical risk minimizationcompactness hypothesisdistance-representation modalitiesnumerical regressionprecedent-based learningpseudo-Euclidean liner spaceselective fusion of distancesset of real-world objects

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) History of computer science (68-03)

Cites Work

• Variable Selection via Nonconcave Penalized Likelihood and its Oracle Properties
• Title not available (Why is that?)
• Support-vector networks
• Regularization and Variable Selection Via the Elastic Net
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• A Statistical View of Some Chemometrics Regression Tools
• The Dissimilarity Representation for Pattern Recognition
• Theoretical foundations of the potential function method in pattern recognition learning
• Title not available (Why is that?)
• Title not available (Why is that?)
• Multiple kernel learning algorithms
• Title not available (Why is that?)
• Encyclopedia of Distances
• A theory of learning with similarity functions
• Title not available (Why is that?)
• The doubly regularized support vector machine
• Dissimilarity representations allow for building good classifiers
• Title not available (Why is that?)
• A unified approach to pattern recognition
• Modeling binary correlated responses using SAS, SPSS and R
• Title not available (Why is that?)

Cited In (3)

• Title not available (Why is that?)
• Title not available (Why is that?)
• On the Concept of Compositional Complexity

This page was built for publication: Compactness Hypothesis, Potential Functions, and Rectifying Linear Space in Machine Learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6104512)