An adaptive Inductive Logic Programming system using Genetic Programming

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@InProceedings{wong:1995:ilpGP,

• author = "Man Leung Wong and Kwong Sak Leung",
• title = "An adaptive Inductive Logic Programming system using Genetic Programming",
• booktitle = "Evolutionary Programming {IV} Proceedings of the Fourth Annual Conference on Evolutionary Programming",
• year = "1995",
• editor = "John Robert McDonnell and Robert G. Reynolds and David B. Fogel",
• pages = "737--752",
• publisher_address = "Cambridge, MA, USA",
• address = "San Diego, CA, USA",
• month = "1-3 " # mar,
• publisher = "MIT Press",
• keywords = "genetic algorithms, genetic programming, Uncle problem",
• ISBN = "0-262-13317-2",
• URL = "http://cptra.ln.edu.hk/~mlwong/conference/ep1995.pdf",
• URL = "http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6300813",
• DOI = "doi:10.7551/mitpress/2887.003.0062",
• size = "16 pages",
• abstract = "Recently, there have been increasing interests in Inductive Logic Programming (ILP) systems. But existing ILP systems cannot improve themselves automatically. This paper describes an Adaptive Inductive Logic Programming (Adaptive ILP) system that evolves during learning. An adaptive ILP system is composed of an external interface, a biases base, a knowledge base of background knowledge, an example database, an empirical ILP learner, a meta-level learner, and a learning controller. A preliminary adaptive ILP system has been implemented. In this implementation, the empirical ILP learner performs top-down search in the hypothesis space defined by the concept description language, the language bias, and the background knowledge. The search is directed by search biases which can be induced and refined by genetic programming (Koza 1992).

  It has been demonstrated that the adaptive ILP system performs better than FOIL, a famous ILP system (Quinlan 1990), in inducing logic programs from perfect or noisy training examples. The experimentation illustrates the benefit of an adaptive ILP system over existing ILP systems. The result implies that the search bias induced by genetic programming (GP) is better than that of FOIL, which is designed by a top researcher in the field. Consequently, GP is a promising technique for implementing a meta-level learning system. The result is very encouraging as it suggests that the process of natural selection and evolution can successfully evolve a high performance ILP system.",

• notes = "EP-95",

}

Genetic Programming entries for Man Leung Wong Kwong-Sak Leung

Citations