Learning criterion and inductive behaviour

https://doi.org/10.1016/0031-3203(78)90044-4Get rights and content

Abstract

Inductive behaviours may be classified according to their aim. We intend to show that there are at least two kinds of inductive behaviours. Most of the publications seem to take into consideration only one of these: to copy as exactly as possible the behaviour of a probability process. After a brief discussion to explain the necessity of a learning criterion and a recall about one criterion, representative of most of them, we shall define a new criterion, and show why it is better fitted to learn the laws of a deterministic process from a set of observations.

This criterion has been used to implement a program which builds an acceptor of natural language sentences in a CAI environment using a tutorial strategy, and then for a question answering device. As attractive as the results are, their improvement requires a semantic model. We give the basic principles of a model which we currently develop, and whose main feature is approximation.

References (20)

  • R.C. Schank
  • J.-C. Simon

    Computer-oriented learning processes

  • S.M. Watanabe

    Information—theoretical aspects of inductive and deductive inference

    IBM J. Res. Dev.

    (April 1960)
  • R.M. Wharton

    Grammatical inference and approximation

  • Alan W. Biermann et al.

    A survey of results in grammatical inference

  • E. Charniak

    Jack and Janet in search of theory of knowledge

  • C.M. Cook et al.

    Some experiments in grammatical inference

  • D. Coulon

    Construction expérimentale d'un modèle informatique pour interpréter des énoncés rédigés en langage naturel

  • D. Coulon et al.

    A supervised-learning technique to identify short natural language sentences

  • K.S. Fu et al.

    Grammatical inference: introduction and survey—1

    IEEE Trans. Syst. Man. Cybern.

    (January 1975)
    K.S. Fu et al.

    Grammatical inference: introduction and survey—II

    IEEE Trans. Syst. Man. Cybern.

    (July 1975)
There are more references available in the full text version of this article.

Cited by (3)

  • Pattern Recognition as Rule-Guided Inductive Inference

    1980, IEEE Transactions on Pattern Analysis and Machine Intelligence

The main part of this work has been done at the Institut de Programmation—Université Paris VI, and has been sponsored by the SESORI (contract No. 73.052). A communication about it has also been done at the 3rd IJCPR congress.(5)

View full text