Back-propagation learning in expert networks
| Autor: | Robert Christopher Lacher, D.C. Kuncicky, S.I. Hruska |
|---|---|
| Rok vydání: | 1992 |
| Předmět: |
Knowledge space
Artificial neural network Computer Networks and Communications business.industry Computer science Supervised learning General Medicine Legal expert system Machine learning computer.software_genre Knowledge acquisition Backpropagation Expert system Computer Science Applications Knowledge extraction Artificial Intelligence Artificial intelligence Types of artificial neural networks business computer Software |
| Zdroj: | IEEE Transactions on Neural Networks. 3:62-72 |
| ISSN: | 1045-9227 |
| DOI: | 10.1109/72.105418 |
| Popis: | 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. > |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|