Abstract
We show that a simple deterministic language is learnable via membership queries in polynomial time if the learner knows a special finite set of positive examples which is called a representative sample. Angluin(1981) showed that a regular language is learnable in polynomial time with membership queries and a representative sample. Thus our result is an extension of her work.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Angluin, D.: A note on the number of queries needed to identify regular languages. Inf. & Cont. 51, 76–87 (1981)
Angluin, D.: Learning regular sets from queries and counterexamples. Inf. & Comp. 75, 87–106 (1987)
Hopcroft, J.E., Ullman, J.D.: Introduction to Automata Theory, Languages, and Computation. Addison-Wesley, Reading (1979)
Ishizaka, H.: Polynomial time learnability of simple deterministic languages. Machine Learning 5, 151–164 (1990)
Korenjak, A.J., Hopcroft, J.E.: Simple deterministic languages. In: Proc. IEEE 7th Annu. Symp. on Switching and Automata Theory, pp. 36–46 (1966)
Sakamoto, H.: Language learning from membership queries and characteristic examples. In: Proc. 6th Int. Conf. on Algorithmic Learning Theory - ALT 1995. LNCS (LNAI), vol. 997, pp. 55–65 (1995)
Wakatsuki, M., Tomita, E.: An improved branching algorithm for checking the equivalence of simple DPDA’s and its worst-case time complexity. Trans. of IEICE J74-D-I, 595–603 (1991) (in Japanese)
Yokomori, T.: Learning simple languages in polynomial time. In: Proc. SIG-FAI, JSAI 8801-3, pp. 21–30 (1988)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2000 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tajima, Y., Tomita, E. (2000). A Polynomial Time Learning Algorithm of Simple Deterministic Languages via Membership Queries and a Representative Sample. In: Oliveira, A.L. (eds) Grammatical Inference: Algorithms and Applications. ICGI 2000. Lecture Notes in Computer Science(), vol 1891. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45257-7_23
Download citation
DOI: https://doi.org/10.1007/978-3-540-45257-7_23
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-41011-9
Online ISBN: 978-3-540-45257-7
eBook Packages: Springer Book Archive