# Machine inductive inference and language identification

## Abstract

We show that for some classes ℒ of recursive languages, from the characteristic function of any L in ℒ an approximate decision procedure for L with no more than n+1 mistakes can be (uniformly effectively) inferred in the limit; whereas, in general, a grammar (generation procedure) with no more than n mistakes cannot; for some classes an infinite sequence of perfectly correct decision procedures can be inferred in the limit, but single grammars with finitely many mistakes cannot; and for some classes an infinite sequence of decision procedures each with no more than n+1 mistakes can be inferred, but an infinite sequence of grammars each with no more than n mistakes cannot. This is true even though decision procedures generally contain more information than grammars. We also consider inference of grammars for r.e. languages from arbitrary texts, i.e., enumerations of the languages. We show that for any class of languages ℒ, if some, machine, from arbitrary texts for any L in ℒ, can infer in the limit an approximate grammar for L with no more than 2·n mistakes, then some machine can infer in the limit, for each language in ℒ, an infinite sequence of grammars each with no more than n mistakes. This reduction from 2·n to n is best possible. From these and other results we obtain and compare several natural, inference hierarchies. Lastly we show that if we restrict ourselves to recursive texts, there is a machine which, for any r.e. language, infers in the limit an infinite sequence of grammars each with only finitely many mistakes. We employ recursion theoretic methods including infinitary and ordinary recursion theorems.

## Keywords

Decision Procedure Recursive Function Infinite Sequence Inductive Inference Regular Language## Preview

Unable to display preview. Download preview PDF.

## References

- [An 80a]Angluin, D., “Finding patterns common to a set of strings,” J. of Computer and System Sciences, 21 (1980), 46–62.MathSciNetCrossRefGoogle Scholar
- [An 80b]Angluin, D., “Inductive inference of formal languages from positive data,” Information and Control, 45, 117–135, 1980.MathSciNetCrossRefGoogle Scholar
- [An 81]Angluin, D., “Inference of Reversible Languages,” J. of the ACM, to appear.Google Scholar
- [Ba 74]Barzdin, J., “Two theorems on the limiting synthesis of functions,” Latvii gosudarst. Univ. ucenye Zapiski, 210, 82–88 (Russian), 1974.MathSciNetGoogle Scholar
- [BB 75]Blum, L. and M. Blum, “Toward a mathematical theory of inductive inference,” Information and Control, 28, 125–155, 1975.MathSciNetCrossRefGoogle Scholar
- [Ca 74]Case, J., “Periodicity in generations of automata,” Math. Systems Theory, 8, 15–32, 1974.MathSciNetCrossRefGoogle Scholar
- [CN 82]Case, J. and S. Ngo Manguelle, “Refinements of inductive inference by Popperian machines I, II,” Kybernetika, to appear.Google Scholar
- [CS 78]Case, J. and C. Smith, “Anomaly hierarchies of mechanized inductive inference,” Proceedings 10th ACM Symposium on Theory of Computing, San Diego, Calif., pp. 314–319, 1978.Google Scholar
- [CS 82]Case, J. and C. Smith, “Comparison of identification criteria for machine inductive inference,” Theoretical Computer Science, to appear.Google Scholar
- [Ch 81]Chen, K. J., Tradeoffs in Machine Inductive Inference, Ph.D. Dissertation, Computer Science Department, SUNY at Buffalo, Amherst, New York, 1981.Google Scholar
- [Ch 82]Chen, K. J., “Tradeoffs in the inductive inference of nearly minimal size programs,” Information and Control, to appear in the special issue devoted to papers presented at the Workshop on Recursion Theory in Computer Science held at Purdue University, 1981.Google Scholar
- [Da 82]Daley, R., “On the error correcting power of pluralism in inductive inference,” preprint.Google Scholar
- [Fe 72]Feldman, J., “Some decidability results on grammatical inference and complexity,” Information and Control, 20, 244–262, 1972.MathSciNetCrossRefGoogle Scholar
- [FW 79]Freivald, R. and R. Wiehagen, “Inductive inference with additional information,” Electronische Informationsverarbeitung und Kybernetik, 15, 179–185, 1979.MathSciNetzbMATHGoogle Scholar
- [Go 67]Gold, M., “Language identification in the limit,” Information and Control, 10, 447–474, 1967.MathSciNetCrossRefGoogle Scholar
- [HU 79]Hopcroft, J. and J. Ullman, Introduction to Automata Theory, Languages, and Computation, Addison-Wesley, Reading, Massachusetts, 1979.zbMATHGoogle Scholar
- [KW 80]Klette, R. and R. Wiehagen, “Research in the theory of inductive inference by GDR mathematicians — a survey,” Information Sciences, 22, 149–169, 1980.MathSciNetCrossRefGoogle Scholar
- [MY 78]Machtey, M. and P. Young, An Introduction to the General Theory of Algorithms, North-Holland, New York, 1978.zbMATHGoogle Scholar
- [Mi 76]Minicozzi, E., “Some natural properties of strong-identification in inductive inference,” Theoretical Computer Science, 2, 345–360, 1976.MathSciNetCrossRefGoogle Scholar
- [OW 82a]Osherson, D. and S. Weinstein, “A note on formal learning theory,” Cognition, 11 (1982), 77–88.CrossRefGoogle Scholar
- [OW 82b]Osherson, D. and S. Weinstein, “Criteria of language learning,” preprint.Google Scholar
- [Pi 79]Pinker, S., “Formal models of language learning,” Cognition, 7 (1979), 217–283.CrossRefGoogle Scholar
- [Ro 58]Rogers, H., “Gödel numberings of the partial recursive functions,” J. of Symbolic logic, 23, 331–341, 1958.MathSciNetCrossRefGoogle Scholar
- [Ro 67]Rogers, H., Theory of Recursive Functions and Effective Computability, McGraw-Hill, New York, 1967.zbMATHGoogle Scholar
- [Sm 81]Smith, C., “The power of parallelism for automatic program synthesis,” Proceedings of the 22nd FOCS Conference, Nashville, Tennessee, October, 1981 (to appear revised in J. of the ACM).Google Scholar
- [We 82]
- [WC 80]Wexler, K. and P. Culicover, Formal Principles of Language Acquisition, MIT Press, Cambridge, Massachusetts, 1980.Google Scholar
- [Wi 77]Wiehagen, R., “Identification of Formal Languages,” Lecture Notes in Computer Science, 53, 571–579, 1977.MathSciNetCrossRefGoogle Scholar