BRICS · Contents · References · Lecturer · Programme · Participation

Inductive Logic Programming

A BRICS Mini-Course
May 20-23, 1997

Lectures by Nada Lavrac
Department of Intelligent Systems
Jozef Stefan Institute
Ljubljana, Slovenija

and Peter Flach
Infolab, Department of Management Information Science
Tilburg University, Holland

Course Contents

Inductive logic programming (ILP) is a research area, combining principles of inductive machine learning and logic programming. ILP aims at a formal framework and practical algorithms for inductively learning relational descriptions in the form of logic programs. ILP is of interest to inductive machine learning as it significantly extends the usual attribute-value representation and consequently enlarges the scope of machine learning applications; it is also of interest to logic programming as it extends the basically deductive framework of logic programming towards the use of induction. The course aims at giving an overview of the field, with an emphasis on the foundations and basic techniques.

ILP has already shown its potential for applications. Applications in a machine learning context include: knowledge acquisition, inductive data engineering, scientific discovery and knowledge discovery in databases. Potential applications in logic programming include: knowledge base updating, logic program synthesis, debugging and verification of programs, and deriving integrity constraints from databases.

References

List of References

The Lecturer

Nada Lavrac has been a research associate at the Department of Intelligent Systems, J. Stefan Institute, Ljubljana, Slovenia (since 1978) and a visiting professor at the Klagenfurt University, Austria (since 1987). She was a visiting researcher at the University of Illinois, the George Mason University and the Katholieke Universiteit Leuven, and has held graduate courses at the universities of Stockholm, Linkoping and Sao Paulo.

Her early research interests were in knowledge-based systems, qualitative modeling and logic programming. She participated in the KARDIO project, developing a knowledge acquisition paradigm based on qualitative modeling and machine learning, described in the book by I. Bratko, I. Mozetic and N. Lavrac: "KARDIO: A Study in Deep and Qualitative Knowledge for Expert Systems", The MIT Press, 1989. Her current research interest is in machine learning, in particular Inductive Logic Programming (ILP). Much of her recent work is described in the book by N. Lavrac and S. Dzeroski: "Inductive Logic Programming: Techniques and Applications", Ellis Horwood 1994.

Nada Lavrac is the scientific coordinator of the European Scientific Network in Inductive Logic Programming ILPNET (1993-1996) and is one of the project managers of the ESPRIT IV project Inductive Logic Programming II (1996-1998). She has been involved in the organization of many international workshops and conferences on Machine Learning and Inductive Logic Programming, including EWSL-87 (I. Bratko and N. Lavrac (eds.): Progress in Machine Learning, SIGMA Press, 1987) and ECML-95 (N. Lavrac and S. Wrobel (eds.): Machine Learning: ECML-95 - Proceedings of 8th European Machine Learning Conference, Springer, 1995).

Peter Flach has been assistant professor in Computer Science at Tilburg University, the Netherlands, since 1988. His research interests include Inductive Logic Programming, logical foundations of induction, and intelligent reasoning. He recently published a textbook on intelligent reasoning, which gives practical Prolog implementations of many logical AI techniques such as theorem proving, model generation, language understanding, abduction, default reasoning, and induction (Simply Logical: intelligent reasoning by example, John Wiley, 1994).

Peter Flach is involved in the ESPRIT IV project Inductive Logic Programming II (1996-1998) and the European Scientific Network in Inductive Logic Programming ILPNET (1993-1996). He is acting secretary of IFIP Working Group 12.2 on Machine Learning. He has served on the Program Committees of several workshops on Algorithmic Learning Theory and Inductive Logic Programming.