A polynomial time incremental algorithm for learning DFA
- 123 Downloads
We present an efficient incremental algorithm for learning deterministic unite state automata (DFA) from labeled examples and membership queries. This algorithm is an extension of Angluin's ID procedure to an incremental framework. The learning algorithm is intermittently provided with labeled examples and has access to a knowledgeable teacher capable of answering membership queries. The learner constructs an initial hypothesis from the given set of labeled examples and the teacher's responses to membership queries. If an additional example observed by the learner is inconsistent with the current hypothesis then the hypothesis is modified minimally to make it consistent with the new example. The update procedure ensures that the modified hypothesis is consistent with all examples observed thus far. The algorithm is guaranteed to converge to a minimum state DFA corresponding to the target when the set of examples observed by the learner includes a live complete set. We prove the convergence of this algorithm and analyze its time and space complexities.
KeywordsRegular Language Learner Construct Incremental Algorithm State Transition Diagram Membership Query
Unable to display preview. Download preview PDF.
- [BF72]A. Biermann and J. Feldman. A survey of results in grammatical inference. In S. Watanabe, editor, Frontiers of Pattern Recognition, Academic Press, pages 31–54, 1972.Google Scholar
- [CM96]D. Carmel and S. Markovitch. Learning models of intelligent agents. In Proceedings of the AAAI-96 (vol. 1), AAAI Press/MIT Press, pages 62–67, 1996.Google Scholar
- [Dup96]P. Dupont. Incremental regular inference. In L. Miclet and C. Higuera, editors, Proceedings of the Third ICGI-96, Montpellier, France, Lecture Notes in Artificial Intelligence 1147, Springer-Verlag, pages 222–237, 1996.Google Scholar
- [FB75]K. S. Fu and T. L. Booth. Grammatical inference: Introduction and survey (part 1). IEEE Transactions on Systems, Man and Cybernetics, 5:85–111, 1975.Google Scholar
- [Lan95]P. Langley. Elements of Machine Learning. Morgan Kauffman, Palo Alto, CA, 1995.Google Scholar
- [MQ86]L. Miclet and J. Quinqueton. Learning from examples in sequences and grammatical inference. In G. Ferrate et al, editors, Syntactic and Structural Pattern Recognition, NATO ASI Series Vol. F45, pages 153–171, 1986.Google Scholar
- [OG92]J. Oncina and P. García. Inferring regular languages in polynomial update time. In N. Pérez et al, editors, Pattern Recognition and Image Analysis, World Scientific, pages 49–61, 1992.Google Scholar
- [PH96]R. G. Parekh and V. G. Honavar. An incremental interactive algorithm for regular grammar inference. In L. Miclet and C. Higuera, editors, Proceedings of the Third ICGI-96, Montpellier, France, Lecture Notes in Artificial Intelligence 1147, Springer-Verlag, pages 238–250, 1996.Google Scholar
- [PH97]R. G. Parekh and V. G. Honavar. Learning dfa from simple examples. In Proceedings of the Eighth International Workshop on Algorithmic Learning Theory (ALT'97), Sendai, Japan, Lecture Notes in Artificial Intelligence 1316, Springer-Verlag, pages 116–131, 1997. Also presented at the Workshop on Grammar Inference, Automata Induction, and Language Acquisition (ICML'97), Nashville, TN. July 12, 1997.Google Scholar
- [PH98]R. G. Parekh and V. G. Honavar. Grammar inference, automata induction, and language acquisition. In R. Dale, H. Moisl, and H. Somers, editors, Handbook of Natural Language Processing. Marcel Dekker, 1998. (To appear).Google Scholar
- [Pit89]L. Pitt. Inductive inference, dfas and computational complexity. In Analogical and Inductive Inference, Lecture Notes in Artificial Intelligence 397, Springer-Verlag, pages 18–44, 1989.Google Scholar