RUTH: an ILP theory revision system
We present the system RUTH (Revising and Updating THeories) which represents an incremental ILP approach to theory revision. The approach integrates intensional database updating and incremental concept-learning. RUTH uses a set of operators in order to make a given knowledge base consistent w.r.t. a user input integrity theory.
Important is that apart from adding and deleting clauses and facts, we also employ an abductive operator, which allows RUTH to introduce missing factual knowledge into the knowledge base. In order to guide the search, several heuristics are used, on top of an intelligent search strategy derived from iterative deepening.
keywordsTheory Revision Inductive Logic Programming
Unable to display preview. Download preview PDF.
- 1.H. Adé, L. De Raedt, and M. Bruynooghe. Theory revision. In Proceedings of the 3rd International Workshop on Inductive Logic Programming, 1993.Google Scholar
- 2.H. Adé, L. De Raedt, and M. Bruynooghe. Declarative Bias for Specific-To-General ILP Systems. To appear in Machine Learning, 1994.Google Scholar
- 3.H. Adé, B. Malfait, and L. De Raedt. Ruth: an ILP Theory Revision System. Technical Report CW-194, Department of Computer Science, Katholieke Universiteit Leuven, 1994.Google Scholar
- 4.Francois Bry. Intensional updates: abduction via deduction. In D. Warren and P. Szeredi, editors, Proceedings of the 7th International Conference on Logic Programming, pages 561–578. The MIT Press, 1990.Google Scholar
- 5.L. De Raedt. Interactive Theory Revision: an Inductive Logic Programming Approach. Academic Press, 1992.Google Scholar
- 6.L. De Raedt and M. Bruynooghe. Belief updating from integrity constraints and queries. Artificial Intelligence, 53:291–307, 1992.Google Scholar
- 7.A. Guessoum and J.W. Lloyd. Updating knowledge bases. New Generation Computing, 8:71–88, 1990.Google Scholar
- 8.R. Korf. Depth-first iterative deepening: an optimal admissable search. Artificial Intelligence, pages 97–109, 1985.Google Scholar
- 9.J.W. Lloyd. Foundations of logic programming. Springer-Verlag, 2nd edition, 1987.Google Scholar
- 10.B. Malfait. Een incrementele, niet-interactieve aanpak van het Theory Revision-probleem binnen ILP. Master's thesis, Department of Computer Science, Katholieke Universiteit Leuven, 1994. in Dutch.Google Scholar
- 11.S. Muggleton and L. De Raedt. Inductive logic programming: Theory and methods. Journal of Logic Programming, 1994. To appear.Google Scholar
- 12.M. Pazzani and C. Brunk. Detecting and correcting errors in rule-based expert systems: an integration of empirical and explanation-based learning. Knowledge Acquisition, 3:157–173, 1991.Google Scholar
- 13.B.L. Richards and R.J. Mooney. First order theory revision. In Proceedings of the 8th International Workshop on Machine Learning, pages 447–451. Morgan Kaufmann, 1991.Google Scholar
- 14.C. Sammut and R. Banerji. Learning concepts by asking questions. In R.S Michalski, J.G. Carbonell, and T.M. Mitchell, editors, Machine Learning: an artificial intelligence approach, volume 2, pages 167–192. Morgan Kaufmann, 1986.Google Scholar
- 15.E.Y. Shapiro. Algorithmic Program Debugging. The MIT Press, 1983.Google Scholar
- 16.S. Tankitvanitch and M. Shimura. Refining a relational theory with multiple faults in the concept and subconcepts. In Proceedings of the 9th International Workshop on Machine Learning, pages 436–444. Morgan Kaufmann, 1992.Google Scholar
- 17.A. Tomasic. View update translation via deduction and annotation. In Proceedings 2nd International Conference on Database Theory, volume 326 of Lecture Notes in Computer Science, pages 338–351. Springer-Verlag, 1988.Google Scholar
- 18.J. Wogulis. Revising relational theories. In Proceedings of the 8th International Workshop on Machine Learning, pages 462–466. Morgan Kaufmann, 1991.Google Scholar