Learning and Classifying

  • Sanjay Jain
  • Eric Martin
  • Frank Stephan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6925)

Abstract

We define and study a learning paradigm that sits between identification in the limit and classification. More precisely, we expect that a learner be able to identify in the limit which members of a set D of n possible data belong to a target language, where n and D are arbitrary. We show that Ex- and BC-learning are often more difficult than performing this classification task, taking into account desirable constraints on how the learner behaves, such as bounding the number of mind changes and being conservative. Special attention is given to various forms of consistency. We provide a fairly comprehensive set of results that demonstrate the fruitfulness of the approach and the richness of the paradigm.

Keywords

Initial Segment Unique Member Recursive Function Inductive Inference Boolean Combination 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [Ang80]
    Angluin, D.: Inductive inference of formal languages from positive data. Information and Control 45, 117–135 (1980)MathSciNetCrossRefMATHGoogle Scholar
  2. [Bār74a]
    Bārzdiņš, J.: Inductive inference of automata, functions and programs. In: Proceedings of the 20th International Congress of Mathematicians, Vancouver, pp. 455–560 (1974) (in Russian); English translation in American Mathematical Society Translations: Series 2, 109, 107–112 (1977)Google Scholar
  3. [Bār74b]
    Bārzdiņš, J.: Two theorems on the limiting synthesis of functions. In: Theory of Algorithms and Programs, vol. 1, pp. 82–88. Latvian State University (1974) (in Russian)Google Scholar
  4. [BB75]
    Blum, L., Blum, M.: Toward a mathematical theory of inductive inference. Information and Control 28(2), 125–155 (1975)MathSciNetCrossRefMATHGoogle Scholar
  5. [CKSS97]
    Case, J., Kinber, E., Sharma, A., Stephan, F.: On the classification of computable languages. In: Reischuk, R., Morvan, M. (eds.) STACS 1997. LNCS, vol. 1200, pp. 225–236. Springer, Heidelberg (1997)CrossRefGoogle Scholar
  6. [CL82]
    Case, J., Lynes, C.: Machine inductive inference and language identification. In: Nielsen, M., Schmidt, E.M. (eds.) ICALP 1982. LNCS, vol. 140, pp. 107–115. Springer, Heidelberg (1982)CrossRefGoogle Scholar
  7. [CS83]
    Case, J., Smith, C.: Comparison of identification criteria for machine inductive inference. Theoretical Computer Science 25, 193–220 (1983)MathSciNetCrossRefMATHGoogle Scholar
  8. [FH94]
    Freivalds, R., Hoffmann, A.: An inductive inference approach to classification. Journal of Experimental and Theoretical Artificial Intelligence 6, 63–72 (1994)CrossRefMATHGoogle Scholar
  9. [Gol67]
    Gold, E.M.: Language identification in the limit. Information and Control 10(5), 447–474 (1967)MathSciNetCrossRefMATHGoogle Scholar
  10. [Jai01]
    Jain, S.: On an open problem in classification of languages. Journal of Experimental and Theoretical Artificial Intelligence 13(2), 113–118 (2001)MathSciNetCrossRefMATHGoogle Scholar
  11. [JB81]
    Jantke, K.P., Beick, H.-R.: Combining postulates of naturalness in inductive inference. Journal of Information Processing and Cybernetics (EIK) 17, 465–484 (1981)MathSciNetMATHGoogle Scholar
  12. [JMS08]
    Jain, S., Martin, E., Stephan, F.: Absolute versus probabilistic classification in a logical setting. Theoretical Computer Science A 397(1-3), 114–128 (2008); Special Issue on Forty Years of Inductive InferenceMathSciNetCrossRefMATHGoogle Scholar
  13. [JORS99]
    Jain, S., Osherson, D., Royer, J., Sharma, A.: Systems that Learn: An Introduction to Learning Theory, 2nd edn. MIT Press, Cambridge (1999)Google Scholar
  14. [OW82]
    Osherson, D., Weinstein, S.: Criteria of language learning. Information and Control 52, 123–138 (1982)MathSciNetCrossRefMATHGoogle Scholar
  15. [Rog67]
    Rogers, H.: Theory of Recursive Functions and Effective Computability. McGraw-Hill, New York (1967); Reprinted by MIT Press in 1987MATHGoogle Scholar
  16. [Ste01]
    Stephan, F.: On one-sided versus two-sided classification. Archive for Mathematical Logic 40, 489–513 (2001)MathSciNetCrossRefMATHGoogle Scholar
  17. [SWZ97]
    Smith, C., Wiehagen, R., Zeugmann, T.: Classifying predicates and languages. International Journal of Foundations of Computer Science 8, 15–41 (1997)CrossRefMATHGoogle Scholar
  18. [WL76]
    Wiehagen, R., Liepe, W.: Charakteristische Eigenschaften von erkennbaren Klassen rekursiver Funktionen. Journal of Information Processing and Cybernetics (EIK) 12, 421–438 (1976)MathSciNetMATHGoogle Scholar
  19. [WS95]
    Wiehagen, R., Smith, C.H.: Generalization versus classification. Journal of Experimental and Theoretical Artificial Intelligence 7, 163–174 (1995)CrossRefMATHGoogle Scholar
  20. [ZZ08]
    Zeugmann, T., Zilles, S.: Learning recursive functions: A survey. Theoretical Computer Science A 397(1-3), 4–56 (2008); Special Issue on Forty Years of Inductive Inference. Dedicated to the 60th Birthday of Rolf WiehagenMathSciNetCrossRefMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2011

Authors and Affiliations

  • Sanjay Jain
    • 1
  • Eric Martin
    • 2
  • Frank Stephan
    • 3
  1. 1.Department of Computer ScienceNational University of SingaporeSingaporeRepublic of Singapore
  2. 2.School of Computer Science and EngineeringThe University of New South WalesSydneyAustralia
  3. 3.Department of Mathematics and Department of Computer ScienceNational University of SingaporeSingaporeRepublic of Singapore

Personalised recommendations