Skip to main content
SpringerLink
Log in

On the complexity of induction of structural descriptions

  • Published:
Journal of Computer Science and Technology Aims and scope Submit manuscript

Abstract

Inductive learning is an important subject in artificial intelligence. As a concern of theoretical computer science, this paper investigates the complexity of induction of structural descriptions which is fundamental to inductive learning. The general complexity is derived, and a way of approaching the induction, namely, computing the maximal common generalizations by pairing, is also presented with its inherent complexity.

A group ofNP-complete andNP-hard problems are introduced when showing the complexities.

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. P. R. Cohen and E. A. Feigenbaum, The handbook of artificial intelligence, Vol. 3, (Eds.) Kaufmann, Los Altos, Calif., 1982.

    MATH  Google Scholar 

  2. T. G. Dietterich and R. S. Michalski, Inductive learning of structural descriptions,Artificial Intelligence,16 (1981), 257–294.

    Article  MathSciNet  Google Scholar 

  3. T. G. Dietterich and R. S. Michalski, Learning and generalization of characteristic descriptions, IJCAI-79, 223–231.

  4. F. Hayes-Roth and J.McDermott, Knowledge aquisition from structural descriptions, IJCAI-77, 356-62.

  5. F. Hayes-Roth and J. McDermott, An interference matching technique for inducing abstractions,C. ACM,21:5(1978), 401–410.

    Article  MATH  Google Scholar 

  6. E. Horowitz and S. Sahni, Eds., Fundamentals of computer algorithms, 1978.

  7. R. S. Michalski, Pattern recognition as rule-guided inductive inference,IEEE Trans. Pattern Analysis and Machine Learning,2: 4(1980).

    Google Scholar 

  8. R. S. Michalski, Towards computer-aided induction, IJCAI-77, 319–320.

  9. R. S. Michalski, A theory and methodology of inductive learning,Artificial Intelligence,29 (1983), 111–161.

    Article  MathSciNet  Google Scholar 

  10. T. M. Mitchell, Generalization as search,Artificial Intelligence,18 (1982), 203–226.

    Article  MathSciNet  Google Scholar 

  11. S. A. Vere, Induction of concepts in the predicate calculus, IJCAI-75, 281–287.

  12. S. A. Vere, Induction of relational productions in the presence of background information. IJCAI-77, 349–355.

  13. S. A. Vere, Inductive learning of relational productions, in: D. A. Waterman and F. Hayes-Roth, Eds., Pattern-Directed Inference Systems, 1978.

  14. P. H. Winston, Learning structural descriptions from examples, Ph. D. thesis, Report AI-TR-231, Art. Int. Lab., MIT, Cambridge (1970).

    Google Scholar 

  15. P. H. Wnston Ed., Artificial Intelligence, Reading, Mass, Addison-Wesley, 1977.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Yunnan Teachers University, Kunming

    Lu Xuemiao

Authors
  1. Lu Xuemiao
    View author publications

    You can also search for this author in PubMed Google Scholar

Additional information

This is a partial fulfilment of the author's master degree.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Lu, X. On the complexity of induction of structural descriptions. J. of Comput. Sci. & Technol. 2, 12–21 (1987). https://doi.org/10.1007/BF02943313

Download citation

  • Received:

  • Revised:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02943313

Keywords

Search

Navigation