Symbolic rule extraction with a scaled conjugate gradient version of CLARION

Falas, T; Stafylopatis, A

dc.contributor.author	Falas, T	en
dc.contributor.author	Stafylopatis, A	en
dc.date.accessioned	2014-03-01T02:43:34Z
dc.date.available	2014-03-01T02:43:34Z
dc.date.issued	2005	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31479
dc.subject	Feed Forward Neural Network	en
dc.subject	Hybrid Intelligent System	en
dc.subject	Hybrid System	en
dc.subject	Learning Algorithm	en
dc.subject	Rule Extraction	en
dc.subject	Neural Network	en
dc.subject	Scaled Conjugate Gradient	en
dc.subject.other	Algorithms	en
dc.subject.other	Feedforward neural networks	en
dc.subject.other	Knowledge based systems	en
dc.subject.other	Learning systems	en
dc.subject.other	Multilayer neural networks	en
dc.subject.other	Performance	en
dc.subject.other	Problem solving	en
dc.subject.other	User interfaces	en
dc.subject.other	Conjugate gradient algorithm	en
dc.subject.other	Hybrid intelligent system	en
dc.subject.other	Multi-layer feed-forward neural network	en
dc.subject.other	Q-learning methodology	en
dc.subject.other	Intelligent structures	en
dc.title	Symbolic rule extraction with a scaled conjugate gradient version of CLARION	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1109/IJCNN.2005.1555962	en
heal.identifier.secondary	http://dx.doi.org/10.1109/IJCNN.2005.1555962	en
heal.identifier.secondary	1555962	en
heal.publicationDate	2005	en
heal.abstract	This paper presents a hybrid intelligent system made up of two modules. The bottom sub-symbolic module is a multi-layer feed-forward neural network trained by a modified Q-learning methodology that employs the scaled conjugate gradient algorithm. The top module is a symbolic system (implemented with a neural network built on-line) where rules are extracted from the bottom module during training, in a fashion similar to the CLARION system. The two modules augment each other in an effort to obtain a better performance than both of the modules acting alone in solving a problem. The originality of this work lies in the use of the advanced scaled conjugate learning algorithm in such a hybrid system. It is expected that the use of this algorithm will provide significant improvements in the performance of the overall system and also make it less dependent on user-selected parameters. This paper emphasises the implementation details, since the system is currently under development, rather that concrete experimental results. © 2005 IEEE.	en
heal.journalName	Proceedings of the International Joint Conference on Neural Networks	en
dc.identifier.doi	10.1109/IJCNN.2005.1555962	en
dc.identifier.volume	2	en
dc.identifier.spage	845	en
dc.identifier.epage	848	en