Learning concepts described by weight aggregation logic

DOI10.4230/LIPICS.CSL.2021.10MaRDI QIDQ6839830zbMATH OpenFDO

Authors Steffen van Bergerem, Nicole Schweikardt

Publication date 23 March 2026

Copyright license Creative Commons Attribution 3.0 Unported

Full work available at URL https://doi.org/10.4230/LIPICS.CSL.2021.10

zbMATH Keywords

localityclassification problemsfirst-order logic with countingFeferman-Vaught decompositionGaifman normal formagnostic probably approximately correct learningfirst-order definable concept learningweight aggregation logic

Mathematics Subject Classification ID

Logic in computer science (03B70) Computer science (68-XX)

Cites work

• scientific article; zbMATH DE number 3819693 (Why is no real title available?)
• scientific article; zbMATH DE number 6999908 (Why is no real title available?)
• scientific article; zbMATH DE number 795584 (Why is no real title available?)
• scientific article; zbMATH DE number 7561484 (Why is no real title available?)
• A theory of the learnable
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Elements of finite model theory.
• First-order logic with counting: at least, \textit{weak} Hanf normal forms always exist and can be computed!
• Gaifman normal forms for counting extensions of first-order logic
• Learnability and definability in trees and similar structures
• Learning concepts definable in first-order logic with counting
• Learning first-order definable concepts over structures of small degree
• Logic, graphs, and algorithms
• Queries and concept learning
• Understanding machine learning. From theory to algorithms

Cited in

(3)

• Learning concepts definable in first-order logic with counting
• The parameterized complexity of learning monadic second-order logic
• On the VC dimension of first-order logic with counting and weight aggregation

This page was built for publication: Learning concepts described by weight aggregation logic

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6839830)