Back-propagation learning in expert networks

Author

Lacher, R.C. ; Hruska, Susan I. ; Kuncicky, David C.

Author_Institution

Dept. of Comput. Sci., Florida State Univ., Tallahassee, FL, USA

Volume

3

Issue

1

fYear

1992

fDate

1/1/1992 12:00:00 AM

Firstpage

62

Lastpage

72

Abstract

Expert networks are event-driven, acyclic networks of neural objects derived from expert systems. The neural objects process information through a nonlinear combining function that is different from, and more complex than, typical neural network node processors. The authors develop back-propagation learning for acyclic, event-driven networks in general and derive a specific algorithm for learning in EMYCIN-derived expert networks. The algorithm combines back-propagation learning with other features of expert networks, including calculation of gradients of the nonlinear combining functions and the hypercube nature of the knowledge space. It offers automation of the knowledge acquisition task for certainty factors, often the most difficult part of knowledge extraction. Results of testing the learning algorithm with a medium-scale (97-node) expert network are presented

Keywords

expert systems; hypercube networks; knowledge acquisition; learning systems; neural nets; EMYCIN-derived; acyclic networks; back-propagation learning; certainty factors; expert networks; expert systems; gradients; hypercube nature; knowledge acquisition task; knowledge space; learning algorithm; neural objects; nonlinear combining function; Application software; Automation; Expert systems; History; Hypercubes; Intelligent networks; Knowledge acquisition; Neural networks; Supervised learning; Testing;

fLanguage

English

Journal_Title

Neural Networks, IEEE Transactions on

Publisher

ieee

ISSN

1045-9227

Type

jour

DOI

10.1109/72.105418

Filename

105418