Skip to main content
SpringerLink
Log in

On case-based learnability of languages

  • Special Issue
  • Published:
New Generation Computing Aims and scope Submit manuscript

Abstract

Case-based reasoning is deemed an important technology to alleviate the bottleneck of knowledge acquisition in Artificial Intelligence (AI). In case-based reasoning, knowledge is represented in the form of particular cases with an appropriate similarity measure rather than any form of rules. The case-based reasoning paradigm adopts the view that an Al system is dynamically changing during its life-cycle which immediately leads to learning considerations.

Within the present paper, we investigate the problem of case-based learning of indexable classes of formal languages. Prior to learning considerations, we study the problem of case-based representability and show that every indexable class is case-based representable with respect to a fixed similarity measure. Next, we investigate several models of case-based learning and systematically analyze their strengths as well as their limitations. Finally, the general approach to case-based learnability of indexable classes of formal languages is prototypically applied to so-called containmet decision lists, since they seem particularly tailored to case-based knowledge processing.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Aha, D. W., Kibler, D., and Albert, M. C., “Instance-Based Learning Algorithms,”Machine Learning, 6, pp. 37–66, 1991.

    Google Scholar 

  2. Angluin, D., “Inductive Inference of Formal Languages from Positive Data,”Information and Control, 45, pp. 117–135, 1980.

    Article  MATH  MathSciNet  Google Scholar 

  3. Angluin, D. and Smith, C. H., “Inductive Inference: Theory and Methods,”ACM Computing Surveys, 15, pp. 237–269, 1983.

    Article  MathSciNet  Google Scholar 

  4. Blum, L. and Blum, M., “Toward a Mathematical Theory of Inductive Inference,”Information and Control, 28, pp. 122–155, 1975.

    Article  MathSciNet  Google Scholar 

  5. Bakhtari, S., Börner, K., Bartsch-Spörl, B., Coulon, C.-H., Janetzko. D., Knauff, M., Hovestadt, L., and Schlieder, C., “EWCBR 93: Contributions of FABEL,”FABEL-Report, 17, Gesellschaft für Mathematik und Datenverarbeitung, 1993.

  6. Burghardt, U., Dötsch, V., and Frind, S., “TIC—Ein Testrahmen für IND-CBL,”CALG 01/96, HTWK Leipzig, Fachbereich IMN, Forschungsgruppe Algorithmisches Lernen, 1996.

  7. Coulon, C.-H., Gebhardt, F., “Evaluation of Retrieval Methods in Case-Based Design,”FABEL-Report, 24, Gesellshaft für Mathematik und Datenverarbeitung, 1994.

  8. Cost, S. and Salzberg, S., “A Weighted Nearest Neighbor Algorithm for Learning with Symbolic Features,”Machine Learning, 10, pp. 57–78, 1993.

    Google Scholar 

  9. Globig, C. and Lange, S., “Case-Based Representability of Classes of Boolean Functions,” inProceedings of 12th European Conference on Artificial Intelligence (ECAI 96), John Wiley & Sons, 1996, to appear.

  10. Gold, E. M., “Language Identification in the Limit,”Information and Control, 10, pp. 447–474, 1967.

    Article  MATH  Google Scholar 

  11. Hoperoft, J. E. and Ullman, J. D.,Introduction to Automata Theory, Languages, and Computation, Addison-Wesley, 1979.

  12. Jantke, K. P., “Case-Based Learning in Inductive Inference,” inProceedings of 5th Workshop on Computational Learning Theory (COLT’92), ACM Press, pp. 218–223, 1992.

  13. Jantke, K. P., “Types of Incremental Learning,” inWorking Notes, AAAI Spring Symposium on Training Issues in Incremental Learning, Stanford University, pp. 26–32, 1993.

  14. Jantke K. P. and Lange, S., “Case-Based Representation and Learning of Pattern Languages,” inProceedings of 4th Workshop on Algorithmic Learning Theory (ALT’93), Lecture Notes in Artificial Intelligence 744, Springer-Verlag, pp. 87–100, 1993.

  15. Jantke, K. P. and Lange, S., “Case-Based Representation and Learning of Pattern Languages,”Theoretical Computer Science, 137, pp. 25–51, 1995.

    Article  MATH  MathSciNet  Google Scholar 

  16. Kolodner, J. L., “An Introduction to Case-Based Reasoning,”Artificial Intelligence Review, 6, pp. 3–34, 1992.

    Article  Google Scholar 

  17. Kolodner, J. L.,Case-Based Reasoning, Morgan Kaufmann, 1993.

  18. Riesbeck, C. K. and Schank, R. C.,Inside Case-Based Reasoning, Lawrence Erlbaum Assoc., 1989.

  19. Rivest, R. L., “Learning Decision Lists,”Machine Learning, 2, pp. 229–246, 1987.

    MathSciNet  Google Scholar 

  20. Sakakibara, Y. and Siromoney, R., “A Noise Model on Learning Sets of Strings,” inProceedings of 5th Workshop on Computational Learning Theory (COLT’92), ACM Press, pp. 295–302, 1992.

  21. Zeugmann, T. and Lange, S., “A Guided Tour Across the Boundaries of Learning Recursive Languages,” inAlgorithmic Learning for Knowledge-Based Systems (Klaus P. Jantke and Steffen Lange, eds.), Springer-Verlag, pp. 190–258, 1995.

Download references

Author information

Authors and Affiliations

  1. FB Informatik, Universität Kaiserslautern, PF 3049, 67653, Kaiserslautern

    Christoph Globig

  2. FB IMN, HTWK Leipzig, PF 30066, 04251, Leipzig, Germany

    Klaus P. Jantke & Steffen Lange

  3. Fujitsu Laboratories Ltd., Institute for Social Information Science, 140, Miyamoto, 410-03, Numazu, Shizuoka, Japan

    Yasubumi Sakakibara

Authors
  1. Christoph Globig
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Klaus P. Jantke
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Steffen Lange
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yasubumi Sakakibara
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

This work summarizes and extends results from the authors’ papers in theProceedings of the 4th International Workshop on Analogical and Inductive Inference andthe 5th International Workshop on Algorithmic Learning Theory, Lecture Notes in Artificial Intelligence 872, Springer-Verlag, Berlin Heidelberg, 1994, pp. 106–120 and pp. 532–546, respectively.

Christoph Globig: He has studied Computer Science at the University of Kaiserslautern and graduated in 1993 with a Master Thesis on a comparison of inductive and case-based learning. Since 1993, he is member of the research group of Prof. Richter at the University of Kaiserslautern. His main research interest is in Machine Learning especially the foundations of case-based reasoning and Machine Learning.

Klaus P. Jantke: He graduated from Humboldt University Berlin with a Master’s Thesis in 1975. He received his Ph.D. in Computer Science in 1979 and his Habilitation at Humboldt in 1984. He worked as the Head of a Research Laboratory in Theoretical Computer Science and as a Vice-Director of the Computing Center at Humboldt University. Since 1987, Dr. Jantke is full professor at Leipzig University of Technology. His main research interest is in algorithmic learning theory. Besides this, he contributes to case-based reasoning, where his special interest is in learning issues and in structural similarity, and to knowledge-based process supervision and control, especially to planning. Dr. Jantke is member of the ACM, the EATCS, and the GI.

Steffen Lange: He graduated from Humboldt University Berlin with a Master’s Thesis in 1984. He received his Ph.D. in Computer Science at Humboldt University Berlin in 1988. Since 1989, Dr. Lange works at Leipzig University of Technology (nowadays HTWK Leipzig) within several research projects on algorithmic learning theory and related topics. His main scientific interest is in algorithmic learning theory. Besides this, he is interested in case-based reasoning, where his work is concentrated on both knowledge representation issues and learning issues.

Yasubumi Sakakibara: He received the B. Sc., M. Sc., and Dr. Sc. degrees from the Department of Information Sciences, Tokyo Institute of Technology, in 1983, 1985, and 1991, respectively. He is currently an associate professor at the Department of Information Sciences, Tokyo Denki University. From 1985 to 1996, he was a researcher at the Institute for Social Information Science (ISIS), Fujitsu Laboratories Ltd.. His current interest includes computational learning theory, formal language theory, complexity theory, statistical theory, and their applications. He is a member of EATCS, IPSJ, JSAI, and JSSST.

About this article

Cite this article

Globig, C., Jantke, K.P., Lange, S. et al. On case-based learnability of languages. New Gener Comput 15, 59–83 (1997). https://doi.org/10.1007/BF03037560

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF03037560

Keywords

Search

Navigation