Abstract
We investigate many paradigms of identifications for classes of languages (namely: consistent learning, EX learning, learning with finitely many errors, behaviorally correct learning, and behaviorally correct learning with finitely many errors) in a measure-theoretic context, and we relate such paradigms to their analogues in learning on informants. Roughly speaking, the results say that most paradigms in measure-theoretic learning wrt some classes of distributions (called δ canonical) are equivalent to the corresponding paradigms for identification on informants.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
[An 80] D. Angluin, ‘Inductive inference of formal languages from positive data’, Inform. Control 45(2) 1980, 117–135.
[An 88] D. Angluin, Identifying languages from stochastic examples, Technical Report 614, University of Yale, 1988.
[BB 75] L. Blum and M. Blum, ‘Toward a mathematical theory of inductive inference’, Inform. Control 28(2) (1975), 125–155.
[B 86] P. Billingsey, Probability and Measure, John Wiley and Sons, second edition 1986.
[CS 83] J. Case, C. Smith, ‘Comparison of identification criteria for machine inductive inference’, Theoretical Computer Science 25, (1983), 193–220.
[DJK 96] D. De Jongh, M. Kanazawa, ‘Angluin's theorem for indexed classes of r.e. languages and applications’, Proceedings of COLT 1996, Desenzano sul Garda, ACM, New York 1996, 193–204.
[DMOWS 96] D. De Jongh, E. Martin, D. Osherson, S. Weinstein, ‘A first order framework for learning’, J. van Benthem, A. ter Meulen (eds.), Handbook of Logic and Language, Elsevier Science Publishers, New York 1996.
[G65] E. M. Gold, ‘Language identification in the limit’, Inform. Control 10 (1967), 447–474.
[L79] A. Levy, Basic Set Theory, Springer Verlag, Berlin 1979.
[Mo 96] F. Montagna, ‘Investigations in measure-one identification of classes of languages’, preprint, University of Siena 1996, to appear in Information and Computation.
[Od 89] P. Odifreddi, Classical Recursion Theory, North Holland, Amsterdam 1989.
[Od?] P. Odifreddi, Classical Recursion Theory. Vol. II, book in preparation.
[OSW 86] D. Osherson, M. Stob, S. Weinstein, Systems that Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists, MIT Press, Cambridge, MA 1986.
[P 85] L. Pitt, ‘Probabilistic inductive inference’, PhD thesis, Yale University 1985.
[P 89] L. Pitt, ‘Probabilistic inductive inference’, J. ACM 36(2) (1989), 383–433.
[PS 88] L. Pitt, C. Smith, ‘Probability and plurality for aggregations of learning machines’, Information and Computation 77 (1988), 77–92.
[R 67] H. Rogers, Theory of Recursive Functions and Effective Computability, Mc Graw Hill, New York 1967.
[WFK 84] R. Wiehagen, R. Friewalds, E. Kinber, ‘On the power of probabilistic strategies in inductive inference’, Theoretical Computer Science 28 (1984), 111–133.
[ZL 95] T. Zeugmann, S. Lange, ‘A guided tour across the boundaries of learning recursive languages’, in Algoritmic Learning for Knowledge-Based Systems, Lecture Notes in Artificial Intelligence 961, p. 193–262, Springer Verlag 1995.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Montagna, F., Simi, G. Paradigms in Measure Theoretic Learning and in Informant Learning. Studia Logica 62, 243–268 (1999). https://doi.org/10.1023/A:1026455720278
Issue Date:
DOI: https://doi.org/10.1023/A:1026455720278