论文信息 - A Note on the Query Complexity of Learning DFA (Extended Abstract)

A Note on the Query Complexity of Learning DFA (Extended 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.

Osamu Watanabe | José L. Balcázar | Josep Díaz | Ricard Gavaldà

[1] Leonard Pitt,et al. Reductions among prediction problems: on the difficulty of predicting automata , 1988, [1988] Proceedings. Structure in Complexity Theory Third Annual Conference.

[2] Dana Angluin,et al. Learning Regular Sets from Queries and Counterexamples , 1987, Inf. Comput..

[3] D. Angluin. Queries and Concept Learning , 1988 .

[4] Leslie G. Valiant,et al. A theory of the learnable , 1984, STOC '84.

[5] Osamu Watanabe. A Formal Study of Learning via Queries , 1990, ICALP.

[6] Leonard Pitt,et al. Inductive Inference, DFAs, and Computational Complexity , 1989, AII.