Knowledge acquisition of conjunctive rules using multilayered neural networks

A major bottleneck in developing knowledge‐based systems is the acquisition of knowledge. Machine learning is an area concerned with the automation of this process of knowledge acquisition. Neural networks generally represent their knowledge at the lower level, while knowledge‐based systems use higher‐level knowledge representations. the method we propose here provides a technique that automatically allows us to extract conjunctive rules from the lower‐level representation used by neural networks, the strength of neural networks in dealing with noise has enabled us to produce correct rules in a noisy domain. Thus we propose a method that uses neural networks as the basis for the automation of knowledge acquisition and can be applied to noisy, realworld domains. © 1993 John Wiley & Sons, Inc.

[1]  Paolo Carnevali,et al.  Learning capabilities of Boolean networks , 1989 .

[2]  Gary Josin,et al.  Neural-network heuristics , 1987 .

[3]  G Palm,et al.  Computing with neural networks. , 1987, Science.

[4]  Geoffrey E. Hinton,et al.  Connectionist Architectures for Artificial Intelligence , 1990, Computer.

[5]  Geoffrey E. Hinton Connectionist Learning Procedures , 1989, Artif. Intell..

[6]  Dean A. Pomerleau,et al.  What's hidden in the hidden layers? , 1989 .

[7]  Douglas B. Lenat,et al.  Theory Formation by Heuristic Search , 1983, Artificial Intelligence.

[8]  James L. McClelland,et al.  Explorations in parallel distributed processing: a handbook of models, programs, and exercises , 1988 .

[9]  Ryszard S. Michalski,et al.  A theory and methodology of inductive learning , 1993 .

[10]  Hiroaki Kitano,et al.  Beyond PDP: The Frequency Modulation Neural Network Architecture , 1989, IJCAI.

[11]  L. A. Rendell,et al.  Conceptual knowledge acquisition in search , 1987 .

[12]  Padhraic Smyth,et al.  An Information Theoretic Approach to Rule-Based Connectionist Expert Systems , 1988, NIPS.

[13]  Douglas B. Lenat,et al.  EURISKO: A Program That Learns New Heuristics and Domain Concepts , 1983, Artif. Intell..

[14]  Geoffrey E. Hinton,et al.  The appeal of parallel distributed processing , 1986 .

[15]  Douglas B. Lenat,et al.  The Nature of Heuristics , 1982, Artif. Intell..

[16]  John R. Anderson Acquisition of cognitive skill. , 1982 .

[17]  William E. Jones,et al.  Back-propagation, a generalized delta learning rule , 1987 .

[18]  S. Ohlsson Transfer of training in procedural learning: a matter of conjectures and refutations? , 1987 .

[19]  Richard Fozzard,et al.  A Connectionist Expert System that Actually Works , 1988, NIPS.