摘要: In principle, the version space approach can be applied to any induction problem. However, in some cases representation language for generalizations is so powerful that (1) of update functions are not effectively computable, and (2) contains infinitely many generalizations. The class context-free grammars a simple exhibits these problems. This paper presents an algorithm solves both problems this domain. Given sequence strings, incrementally constructs data structure has nearly all beneficial properties space. fast enough solve small completely, it serves as framework biases permit solution larger heuristically. same basic may representations include special cases, such And-Or graphs, production systems, Horn clauses.
springer.com
elsevier.com
paperity.org参考文章(27)
Pat Langley, Rediscovering physics with BACON.3 international joint conference on artificial intelligence. pp. 505- 507 ,(1979)
Jamie G Carbonell, Pat Langley, Language Acquisition and Machine Learning. ,(1986)
悦朗 守屋, J.E.Hopcroft, J.D. Ullman 著, "Introduction to Automata Theory, Languages, and Computation", Addison-Wesley, A5変形版, X+418, \6,670, 1979 情報処理. ,vol. 21, pp. 802- 803 ,(1980)
Herbert Ginsburg, The development of mathematical thinking Academic Press. ,(1983)
Robert C. Berwick, The acquisition of syntactic knowledge ,(1985)
A.W. Biermann, J.A. Feldman, A SURVEY OF RESULTS IN GRAMMATICAL INFERENCE Frontiers of Pattern Recognition#R##N#The Proceedings of the International Conference on Frontiers of Pattern Recognition. pp. 31- 54 ,(1972) , 10.1016/B978-0-12-737140-5.50007-5
James Jay Horning, A study of grammatical inference Stanford University. ,(1969)
J. G. Carbonell, T. M. Mitchell, R. S. Michalski, Machine Learning: An Artificial Intelligence Approach Springer Publishing Company, Incorporated. ,(2013)
Kurt Alan Vanlehn, Felicity conditions for human skill acquisition: validating an ai-based theory Massachusetts Institute of Technology. ,(1983)
John R. Anderson, The Architecture of Cognition ,(1995)