Back-propagation learning in expert networks
- 1 January 1992
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 3 (1) , 62-72
- https://doi.org/10.1109/72.105418
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
This publication has 10 references indexed in Scilit:
- Learning to Predict and Explain: An Integration of Similarity-Based, Theory-Driven, and Explanation-Based LearningJournal of the Learning Sciences, 1991
- Mapping rule-based systems into neural architectureKnowledge-Based Systems, 1990
- Building expert systems by a modified perceptron network with rule-transfer algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Analogies of brain function in neural network modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- The role of time in natural intelligence: implications for neural network and artificial intelligence researchPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- A Connectionist Approach to Knowledge Representation and Limited InferenceCognitive Science, 1988
- A Distributed Connectionist Production SystemCognitive Science, 1988
- Connectionist expert systemsCommunications of the ACM, 1988
- Continuous versus discrete information processing: Modeling accumulation of partial information.Psychological Review, 1988
- The role of fuzzy logic in the management of uncertainty in expert systemsFuzzy Sets and Systems, 1983