Probabilistic Inductive Logic Programming

by De Raedt, Luc; Frasconi, Paolo; Kersting, Kristian; Muggleton, Stephen

• ISBN13: 9783540786511
• ISBN10: 3540786511
• Format: Paperback
• Copyright: 2008-05-04
• Publisher: Springer-Verlag New York Inc

Summary

The question, how to combine probability and logic with learning, is getting an increased attention in several disciplines such as knowledge representation, reasoning about uncertainty, data mining, and machine learning simulateously. This results in the newly emerging subfield known under the names of statistical relational learning and probabilistic inductive logic programming.This book provides an introduction to the field with an emphasis on the methods based on logic programming principles. It is concerned with formalisms and systems, implementations and applications, as well as with the theory of probabilistic inductive logic programming.The 13 chapters of this state-of-the-art survey start with an introduction to probabilistic inductive logic programming; moreover the book presents a detailed overview of the most important probabilistic logic learning formalisms and systems such as relational sequence learning techniques, using kernels with logical representations, Markov logic, the PRISM system, CLP(BN), Bayesian logic programs, and the independent choice logic. The third part provides a detailed account of some show-case applications of probabilistic inductive logic programming. The final part touches upon some theoretical investigations and includes chapters on behavioural comparison of probabilistic logic programming representations and a model-theoretic expressivity analysis.

Table of Contents

Introduction
Probabilistic Inductive Logic Programming	p. 1
Formalisms and Systems
Relational Sequence Learning	p. 28
Learning with Kernels and Logical Representations	p. 56
Markov Logic	p. 92
New Advances in Logic-Based Probabilistic Modeling by PRISM	p. 118
CLP(BN): Constraint Logic Programming for Probabilistic Knowledge	p. 156
Basic Principles of Learning Bayesian Logic Programs	p. 189
The Independent Choice Logic and Beyond	p. 222
Applications
Protein Fold Discovery Using Stochastic Logic Programs	p. 244
Probabilistic Logic Learning from Haplotype Data	p. 263
Model Revision from Temporal Logic Properties in Computational Systems Biology	p. 287
Theory
A Behavioral Comparison of Some Probabilistic Logic Models	p. 305
Model-Theoretic Expressivity Analysis	p. 325
Author Index	p. 341
Table of Contents provided by Ingram. All Rights Reserved.