Přístupnostní navigace
E-application
Search Search Close
Publication detail
VALENTA, J.
Original Title
Modified back-propagation for rule based systems
Type
conference paper
Language
English
Original Abstract
This paper describes a method to eliminate knowledge engineer from the process of expert system's knowledge base creation. The methods developed for this task are mainly based on fusion of neural networks and rules. Two basic algorithms are shortly presented here and their advantages and shortcomings are noticed. The developed method consists on a modification of back-propagation algorithm to learn the rule base directly. The structure, properties and method of learning are presented. Finally the process of using the algorithm and its main advantages are described.
Keywords
back-propagation, expert system, knowledge-base, learning
Authors
RIV year
2007
Released
1. 10. 2007
Location
Porto, Portugal
ISBN
978-972-99397-5-4
Book
Proceedings of the IASK International Conference E-Activity and Leading Technologies
Edition number
1
Pages from
150
Pages to
154
Pages count
5
BibTex
@inproceedings{BUT28058, author="Jan {Valenta}", title="Modified back-propagation for rule based systems", booktitle="Proceedings of the IASK International Conference E-Activity and Leading Technologies", year="2007", number="1", pages="150--154", address="Porto, Portugal", isbn="978-972-99397-5-4" }