First-order \(jk\)-clausal theories are PAC-learnable

DOI10.1016/0004-3702(94)90112-0zbMath0938.68773OpenAlexW2141288588MaRDI QIDQ1342231

Sašo Džeroski, Luc De Raedt

Publication date: 21 June 2000

Published in: Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0004-3702(94)90112-0

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Formal languages and automata (68Q45)

Related Items

Logical settings for concept-learning, Rule Induction and Reasoning over Knowledge Graphs, Complexity parameters for first order classes, Foundations of Onto-Relational Learning, Inductive Logic Programming in Databases: From <scp>Datalog</scp> to, Learning logic programs with structured background knowledge, Polynomial certificates for propositional classes, Probabilistic Inductive Logic Programming, Classifier-based constraint acquisition, Probabilistic inductive constraint logic, Top-down induction of first-order logical decision trees, Ontology Learning from Interpretations in Lightweight Description Logics, Unnamed Item, Prediction-hardness of acyclic conjunctive queries, Mind change complexity of learning logic programs

Uses Software

• GOLEM

Cites Work

• Flattening and saturation: Two representation changes for generalization
• Grammatically biased learning: Learning logic programs using an explicit antecedent description language
• Probably Approximate Learning of Sets and Functions
• Learnability and the Vapnik-Chervonenkis dimension
• A theory of the learnable
• Inductive Logic Programming: Theory and methods
• Unnamed Item
• Unnamed Item
• Unnamed Item