Abstract
Higman showed that if A is any language then SUBSEQ(A) is regular, where SUBSEQ(A) is the language of all subsequences of strings in A. We consider the following inductive inference problem: given A(ε), A(0), A(1), A(00), ... learn, in the limit, a DFA for SUBSEQ(A). We consider this model of learning and the variants of it that are usually studied in inductive inference: anomalies, mindchanges, and teams.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Baliga, G., Case, J.: Learning with higher order additional information. In: Proc. 5th Int. Workshop on Algorithmic Learning Theory, pp. 64–75. Springer, Heidelberg (1994)
Blum, L., Blum, M.: Towards a mathematical theory of inductive inference. Information and Computation 28, 125–155 (1975)
Case, J., Jain, S., Manguelle, S.N.: Refinements of inductive inference by Popperian and reliable machines. Kybernetika 30(1), 23–52 (1994)
Case, J., Smith, C.H.: Comparison of identification criteria for machine inductive inference. Theoretical Computer Science 25, 193–220 (1983)
Daley, R., Kalyanasundaram, B., Velauthapillai, M.: Breaking the probability 1/2 barrier in FIN-type learning. Journal of Computer and System Sciences 50, 574–599 (1995)
Fenner, S., Gasarch, W., Postow, B.: The complexity of finding SUBSEQ(L) (unpublished manuscript, 2006)
Fortnow, L., Jain, S., Gasarch, W., Kinber, E., Kummer, M., Kurtz, S., Pleszkoch, M., Slaman, T., Stephan, F., Solovay, R.: Extremes in the degrees of inferability. Annals of Pure and Applied Logic 66, 21–276 (1994)
Freivalds, R., Smith, C.H.: On the role of procrastination for machine learning. Information and Computation 107(2), 237–271 (1993)
Freivalds, R., Smith, C.H., Velauthapillai, M.: Trade-off among parameters affecting inductive inference. Information and Computation 82(3), 323–349 (1989)
Gasarch, W., Kinber, E., Pleszkoch, M., Smith, C.H., Zeugmann, T.: Learning via queries, teams, and anomalies. Fundamenta Informaticae 23, 67–89 (1995); Prior version in Computational Learning Theory (COLT) (1990)
Gasarch, W., Lee, A.: Inferring answers to queries. In: Proceedings of 10th Annual ACM Conference on Computational Learning Theory, pp. 275–284 (1997); Long version on Gasarch’s home page, in progress, much expanded
Gasarch, W., Pleszkoch, M., Solovay, R.: Learning via queries to [ + , < ]. Journal of Symbolic Logic 57(1), 53–81 (1992)
Gasarch, W., Pleszkoch, M., Stephan, F., Velauthapillai, M.: Classification using information. In: Annals of Math and AI, pp. 147–168 (1998); Earlier version in Proc. 5th Int. Workshop on Algorithmic Learning Theory, pp. 290–300 (1994)
Gasarch, W., Smith, C.H.: Learning via queries. Journal of the ACM 39(3), 649–675 (1988); Prior version in IEEE Sym. on Found. of Comp. Sci. (FOCS) (1988)
Gold, E.M.: Language identification in the limit. Information and Computation 10(10), 447–474 (1967)
Higman, A.G.: Ordering by divisibility in abstract algebra. Proc. of the London Math Society 3, 326–336 (1952)
Kummer, M., Stephan, F.: On the structure of the degrees of inferability. Journal of Computer and System Sciences 52(2), 214–238 (1996); Prior version in Sixth Annual Conference on Computational Learning Theory (COLT), 1993
Rogers, H.: Theory of Recursive Functions and Effective Computability. McGraw-Hill, New York (1967); Reprinted by MIT Press (1987)
Sacks, G.E.: Higher Recursion Theory. In: Perspectives in Mathematical Logic. Springer, Berlin (1990)
Soare, R.: Recursively Enumerable Sets and Degrees. In: Perspectives in Mathematical Logic. Springer, Berlin (1987)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fenner, S., Gasarch, W. (2006). The Complexity of Learning SUBSEQ (A). In: Balcázar, J.L., Long, P.M., Stephan, F. (eds) Algorithmic Learning Theory. ALT 2006. Lecture Notes in Computer Science(), vol 4264. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11894841_12
Download citation
DOI: https://doi.org/10.1007/11894841_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46649-9
Online ISBN: 978-3-540-46650-5
eBook Packages: Computer ScienceComputer Science (R0)