Abstract
This paper deals with the polynomial-time learnability of a language class in the limit from positive data, and discusses the learning problem of a subclass of deterministic finite automata (DFAs), called strictly deterministic automata (SDAs), in the framework of learning in the limit from positive data. We first discuss the difficulty of Pitt's definition in the framework of learning in the limit from positive data, by showing that any class of languages with an infinite descending chain property is not polynomial-time learnable in the limit from positive data. We then propose new definitions for polynomial-time learnability in the limit from positive data. We show in our new definitions that the class of SDAs is iteratively, consistently polynomial-time learnable in the limit from positive data. In particular, we present a learning algorithm that learns any SDA M in the limit from positive data, satisfying the properties that (i) the time for updating a conjecture is at most O(lm), (ii) the number of implicit prediction errors is at most O(ln), where l is the maximum length of all positive data provided, m is the alphabet size of M and n is the size of M, (iii) each conjecture is computed from only the previous conjecture and the current example, and (iv) at any stage the conjecture is consistent with the sample set seen so far. This is in marked contrast to the fact that the class of DFAs is neither learnable in the limit from positive data nor polynomial-time learnable in the limit.
Article PDF
Similar content being viewed by others
Avoid common mistakes on your manuscript.
References
Angluin, D. (1980). Inductive inference of formal languages from positive data. Information and Control, 45:117–135.
Angluin, D. (1982). Inference of reversible languages. Journal of the ACM, 29:741–765.
Angluin, D. (1987). Learning regular sets from queries and counterexamples. Information and Computation, 75:87–106.
Angluin, D. (1990). Negative results for equivalence queries. Machine Learning, 5:121–150.
Berwick, R.C. & Pilato, S. (1987). Learning syntax by automata induction. Machine Learning, 2:9–38.
Gold, E. M. (1967). Language identification in the limit. Information and Control, 10:447–474.
Gonzalez, R. C. & Thomason, M. G. (1978). Syntactic Pattern Recognition: An Introduction. Addison-Wesley, Reading, Mass.
Hopcroft, J. E. & Ullman, J. D. (1979). Introduction to Automata Theory, Languages, and Computation. Addison-Wesley, Reading, Massachusetts.
Jantke, K.P. & Beick, H-R. (1981). Combining postulates of naturalness in inductive inference. Journal of Information Processing and Cybernetics, 17:465–484.
Mäkinen, E. (1990). The grammatical inference problem for the Szilard languages of linear grammars. Information Processing Letters, 36:203–206.
Osherson, D.N., Stob, M., & Weinstein, S. (1986). Systems That Learn: An introduction to learning theory for cognitive and computer scientists. MIT Press, Cambridge, MA.
Porat, S. & Feldman, J.A. (1991). Learning automata from ordered examples. Machine Learning, 7:109–138, 1991.
Pitt, L. (1989). Inductive inference, DFAs, and computational complexity. In Proceedings of 2st Workshop on Analogical and Inductive Inference, Lecture Notes in Artificial Intelligence, Springer-Verlag 397, pp. 18–44.
Tanida, N. & Yokomori, T. (1992). Polynomial-time identification of strictly regular languages in the limit. IEICE Transactions on Information and Systems, E75-D:125–132.
Valiant, L. (1984). A theory of the learnable. Communications of the ACM, 27:1134–1142.
Wiehagen, R. (1976). Limeserkennung rekursiver funktionen durch spezielle strategien. EIK, pp.93–99.
Wood, D. (1987). Theory of Computation. Harper and Row, New York.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Yokomori, T. On Polynomial-Time Learnability in the Limit of Strictly Deterministic Automata. Machine Learning 19, 153–179 (1995). https://doi.org/10.1023/A:1022615325466
Issue Date:
DOI: https://doi.org/10.1023/A:1022615325466