Projection-Based PILP: Computational Learning Theory with Empirical Results
- 770 Downloads
Evaluations of advantages of Probabilistic Inductive Logic Programming (PILP) against ILP have not been conducted from a computational learning theory point of view. We propose a PILP framework, projection-based PILP, in which surjective projection functions are used to produce a “lossy” compression dataset from an ILP dataset. We present sample complexity results including conditions when projection-based PILP needs fewer examples than PAC. We experimentally confirm the theoretical bounds for the projection-based PILP in the Blackjack domain using Cellist, a system which machine learns Probabilistic Logic Automata. In our experiments projection-based PILP shows lower predictive error than the theoretical bounds and achieves substantially lower predictive error than ILP. To the authors’ knowledge this is the first paper describing both a computer learning theory and related empirical results on an advantage of PILP against ILP.
Unable to display preview. Download preview PDF.
- 3.Mitchell, T.M.: Machine learning. McGraw-Hill (1997)Google Scholar
- 4.Muggleton, S., David Page Jr., C.: A learnability model for universal representations. In: Proceedings of the 4th International Workshop of Inductive Logic Programming, pp. 139–160. GMD (1997)Google Scholar
- 7.Russell, S.J., Norvig, P.: Artifical intelligence: A modern approach, 2nd edn. Prentice Hall (2003)Google Scholar