Abstract
It is known [1] that the class of deterministic finite automata is polynomial time learnable by using membership and equivalence queries. We investigate — the query complexity — the number of membership and equivalence queries for learning deterministic finite automata. We first show two lower bounds in two different learning situations. Then we investigate the query complexity in general setting, and show some trade-off phenomenon between the number of membership and equivalence queries.
This research was partially supported by the ESPRIT II Basic Research Actions Program of the EC under contract. Ko. 3075 (project. ALCOM). The third author was supported in part by the National Science Foundation under grant. CCR.89-13584 while visiting University of California, Santa Barbara. The fourth author was supported in part. by Takayanagi Foundation of Electronics and Science Technology.
Preview
Unable to display preview. Download preview PDF.
References
Angluin, D., Learning regular sets from queries and counterexamples, Information and Computation, Vol. 75, 1987, pp.87–106.
Angluin, D., Queries and concept learning, Machine Learning, Vol. 2, 1988, pp.319–342.
Angluin, D., Negative results for equivalence queries, Machine Learning, Vol. 5, 1990, pp. 121–150.
Balcázar, J.L., Díaz, J., Gavaldà, R., and Watanabe, O., A note on the query complexity of learning DFA, Technical Report 92TR-0009, Dept. of Computer Science, Tokyo Institute of Technology, 1992.
Pitt, L., Inductive inference, DFAs, and computational complexity, in Proc. International Workshop on Analogical and Inductive Inference AII'89, Lecture Notes in Artificial Intelligence 397, Springer-Verlag, 1989, pp.18–42.
Pitt, L., and Warmuth, M., Reductions among prediction problems: on the difficulty of prediction automata, in Proc. 3rd Structure in Complexity Theory Conference, IEEE, 1988, pp.60–69.
Valiant, L., A theory of the learnable, Communications of the ACM, Vol. 27, 1984, pp. 1134–1142.
Watanabe, O., A formal study of learning via queries, in Proc. 17th International Colloquium on Automata, Languages and Programming, Lecture Notes in Computer Science 443, Springer-Verlag, 1990, pp. 137–152.
Watanabe, O., A framework for polynomial time query learnability, Technical Report 92TR-0003, Dept. of Computer Science, Tokyo Institute of Technology, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1993 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Balcázar, J.L., Díaz, J., Gavaldà, R., Watanabe, O. (1993). A note on the query complexity of learning DFA. In: Doshita, S., Furukawa, K., Jantke, K.P., Nishida, T. (eds) Algorithmic Learning Theory. ALT 1992. Lecture Notes in Computer Science, vol 743. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-57369-0_27
Download citation
DOI: https://doi.org/10.1007/3-540-57369-0_27
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-57369-2
Online ISBN: 978-3-540-48093-8
eBook Packages: Springer Book Archive