Knowledge acquisition driven by constructive and interactive induction

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 599)


This paper describes the basic framework and the latest configuration of a knowledge acquisition system named KAISER. This system inductively learns classification knowledge in the form of a decision tree, and analyzes the results and the processes with domain and task specific knowledge to detect improper states. Then it asks suggestive questions to eliminate the improprieties and acquires new domain knowledge for the next induction cycle. One of the final objectives of this research is to frame a unified theory in the classification trees' paradigm arguing: (1) what means to have a good/bad tree; (2) why it is good/bad; and (3) how to obtain a better one. To achieve this goal, KAISER has been enhanced with a meta-leamer named Meta-KAISER to accumulate the meta-knowledge by keeping track of the experts' response of domain level interaction.


Decision Tree Domain Knowledge Knowledge Acquisition Questionnaire Generation Elimination Action 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    J. B. Kruskal: Multidimensional Scaling by Optimizing Goodness of Fit to a Non-metric Hypothesis. Psychometrika 29, 1964Google Scholar
  2. 2.
    O. Kakusho and R. Mizoguchi: A New Algorithm for Non-Linear Mapping with Applications to Dimension and Cluster Analyses. Pattern Recognition 1, 1983Google Scholar
  3. 3.
    J. R. Quinlan: Induction of Decision Trees. Machine Learning 1, 1986Google Scholar
  4. 4.
    C. J. Matheus and L. A. Rendell: Constructive Induction On Decision Trees. Proc. of IJCAI'89, 1989Google Scholar
  5. 5.
    P. B. Brazdil and L. Torgo: Knowledge Acquisition via Knowledge Integration. Current Trends in Knowledge Acquisition, B. Wielinga, J. Boose et al. (Eds.), 1990Google Scholar
  6. 6.
    G. Pagallo and D. Haussler: Boolean Feature Discovery in Empirical Learning. Machine Learning 5, 1990Google Scholar
  7. 7.
    M. J. Pazzani and D. Kibler: The Utility of Knowledge in Inductive Learning. UCI Tech. Rep., TR-90-18, 1990Google Scholar
  8. 8.
    K. Tsujino, M. Takegaki and S. Nishida: A Knowledge Acquisition System That Aims as Integrating Inductive Learning and Explanation-based Reasoning. Proc. of JKAW'90, 1990Google Scholar
  9. 9.
    M. J. Pazzani and C. A. Brunk: Detecting and Correcting Errors in Rule-Based Expert Systems: An Integration of Empirical and Explanation-based Learning. Knowledge Acquisition 3, 1991Google Scholar
  10. 10.
    C. J. Matheus: The Need for Constructive Induction. Proc. of ML'91, 1991Google Scholar
  11. 11.
    K. Tsujino and S. Nishida: A Knowledge Acquisition System driven by Inductive Learning and Deductive Explanation: KAISER. (In Japanese.) Journal of Japanese Society for Artificial Intelligence 7, 1992Google Scholar
  12. 12.
    V. G. Dabija, K. Tsujino and S. Nishida: Theory Formation in the Decision Trees Domain. (In English.) Journal of Japanese Society for Artificial Intelligence 7, 1992Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1992

Authors and Affiliations

  1. 1.System 4G, Central Research LaboratoryMITSUBISHI Electric corp.HyogoJapan

Personalised recommendations