Inductive Logic Programming : 23rd International Conference, ILP 2013, Rio de Janeiro, Brazil, August 28-30, 2013, Revised Selected Papers / / edited by Gerson Zaverucha, Vítor Santos Costa, Aline Paes

• Record Nr.: UNINA9910484814403321
• Pubbl/distr/stampa: Berlin, Heidelberg : , : Springer Berlin Heidelberg : , : Imprint : Springer, , 2014
• ISBN: 3-662-44923-4
• Edizione: [1st ed. 2014.]
• Descrizione fisica: 1 online resource (XIII, 141 p. 31 illus.)
• Collana: Lecture Notes in Artificial Intelligence ; ; 8812
• Disciplina: 005.115
• Soggetti: Mathematical logic; Artificial intelligence; Computer programming; Computer logic; Computers; Application software; Mathematical Logic and Formal Languages; Artificial Intelligence; Programming Techniques; Logics and Meanings of Programs; Computation by Abstract Devices; Information Systems Applications (incl. Internet)
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: Bibliographic Level Mode of Issuance: Monograph
• Nota di bibliografia: Includes bibliographical references and index.
• Nota di contenuto: Intro -- Preface -- Organization -- Contents -- MetaBayes: Bayesian Meta-Interpretative Learning Using Higher-Order Stochastic Refinement -- 1 Introduction -- 1.1 Bayesian MIL Versus Probabilistic ILP -- 1.2 Multiple and Single Models -- 2 MetaBayes Refinement Framework -- 2.1 Setting -- 2.2 Generalised Meta-Interpreter -- 2.3 Stochastic Refinement -- 2.4 Prior, Likelihood and Posterior -- 3 Implementation -- 3.1 MetaBayes -- 3.2 MetaBayesMAP -- 3.3 MetaBayesSiLP -- 3.4 MilProbLog -- 4 Experiments -- 4.1 Binary Prediction - MetaBayes vs. MetaMap -- 4.2 Probabilistic Prediction - MetaBayes vs. MetaBayesSiLP ; vs. MilProbLog -- 5 Related Work -- 6 Conclusion and Further Work -- References -- On Differentially Private Inductive Logic Programming -- 1 Introduction -- 2 Preliminaries -- 2.1 Inductive Logic Programming -- 2.2 Differential Privacy -- 3 Problem Formulation -- 4 Trade-Off on Privacy and Utility -- 4.1 Our Utility Model -- 4.2 A Lower Bound on Privacy Parameter -- 5 Differentially Private ILP Algorithm -- 5.1 A Non-private ILP Algorithm -- 5.2 A Differentially Private Selection Algorithm -- 5.3 A Differentially Private Reduction Algorithm -- 5.4 Our Differentially Private ILP Algorithm -- 6 Experiment -- 7 Conclusion -- References -- Learning Through Hypothesis Refinement Using Answer Set Programming -- 1 Introduction -- 2 Background -- 2.1 Top-Directed Abductive Learning in ASP -- 3 Learning Through Hypothesis Refinement -- 3.1 Hypothesis Refinement -- 3.2 Learning a Partial Hypothesis -- 4 RASPAL: Iterative Learning by Refinement -- 4.1 Algorithms -- 5 Experiment -- 6 Conclusion and Future Work -- References -- A BDD-Based Algorithm for Learning from Interpretation Transition -- 1 Introduction -- 2 Learning from 1-Step Transitions -- 3 BDD Algorithms for LF1T -- 4 Experiments -- 5 Conclusion and Future Work -- A Appendix.; A.1 Proof of Theorem 1 -- References -- Accelerating Imitation Learning in Relational Domains via Transfer by Initialization -- 1 Introduction -- 2 Background -- 3 Relational Imitation Learning -- 4 Relational Transfer -- 5 Experiments -- 6 Discussion and Conclusion -- References -- A Direct Policy-Search Algorithm for Relational Reinforcement Learning -- 1 Introduction -- 2 Related Work -- 3 Terminology -- 3.1 Blocks World -- 4 CERRLA Algorithm -- 4.1 Cross-Entropy Method -- 4.2 Rule Discovery -- 4.3 Policy-Search Process -- 5 Evaluation -- 5.1 Blocks World -- 5.2 Ms.Pac-Man -- 5.3 Carcassonne -- 6 Conclusions -- References -- AND Parallelism for ILP: The APIS System -- 1 Introduction -- 2 Background -- 2.1 Parallel Execution of Logic Programs -- 3 The APIS System -- 3.1 Redundancy Avoidance -- 4 Experiments and Results -- 4.1 Experimental Settings -- 4.2 Results and Discussion -- 5 Parallel Execution of ILP Systems -- 6 Conclusions -- References -- Generalized Counting for Lifted Variable Elimination -- 1 Introduction -- 2 Representation -- 3 Lifted Variable Elimination -- 4 Generalized Counting Formulas -- 4.1 A Motivating Example -- 4.2 Definition -- 5 Conversion Operations -- 5.1 Counting Conversion -- 5.2 Merging Counting Formulas -- 5.3 Merge-Counting -- 6 Elimination Operations -- 6.1 Sum-out by Counting -- 6.2 Aggregation -- 7 Relation to Joint Conversion -- 8 Conclusion -- References -- A FOIL-Like Method for Learning under Incompleteness and Vagueness -- 1 Introduction -- 2 Preliminaries -- 3 Learning Fuzzy EL(D) Axioms -- 3.1 The Problem Statement -- 3.2 The Solution Strategy -- 4 Related Work -- 5 Towards an Application in Tourism -- 6 Conclusions -- References -- Author Index.
• Sommario/riassunto: This book constitutes the thoroughly refereed post-proceedings of the 23rd International Conference on Inductive Logic Programming, ILP 2013, held in Rio de Janeiro, Brazil, in August 2013. The 9 revised extended papers were carefully reviewed and selected from 42 submissions. The conference now focuses on all aspects of learning in logic, multi-relational learning and data mining, statistical relational learning, graph and tree mining, relational reinforcement learning, and other forms of learning from structured data.