
	Journal of Applied Sciences
	Year: 2012 \| Volume: 12 \| Issue: 9 \| Page No.: 840-847 DOI: 10.3923/jas.2012.840.847

Learning Logic Programming in Radial Basis Function Network via Genetic Algorithm

Nawaf Hamadneh, Saratha Sathasivam, Surafel Luleseged Tilahun and Ong Hong Choon

Abstract: Neural-symbolic systems are based on both logic programming and artificial neural networks. A neural network is a black box that clearly learns the internal relations of unknown systems. Radial Basis Function Neural Network (RBFNN) is a commonly-used type of feed forward neural network. Algorithms are used for learning the RBFNN in an adaptive procedure. Learning RBFNN indicate how the parameters (the output weights, the centers and the widths) should be incrementally adapted to improve a predefined performance measure, in this work, we embedded higher order logic programming in RBFNN. k-means cluster algorithm and Genetic Algorithm (GA) used in for training RBFNN.

PDF Fulltext XML References Citation Report Citation

RELATED ARTICLES:

•	Effect of Weight Updates Functions in QSAR/QSPR Modeling using Artificial Neural Network

•	A Novel Optimized Neural Network Model for Cost Estimation using Genetic Algorithm

•	Neural Network Sliding Mode based Current Decoupled Control for Induction Motor Drive

•	Modeling of Wind Speed for Palestine Using Artificial Neural Network

How to cite this article:

Nawaf Hamadneh, Saratha Sathasivam, Surafel Luleseged Tilahun and Ong Hong Choon, 2012. Learning Logic Programming in Radial Basis Function Network via Genetic Algorithm. Journal of Applied Sciences, 12: 840-847.

DOI: 10.3923/jas.2012.840.847

URL: https://scialert.net/abstract/?doi=jas.2012.840.847

COMMENT ON THIS PAPER

Navigation


		Online First
		Current Issue
		Previous Issues
		Editorial Board
		Submit a Manuscript
		Guide to Authors
		Subscribe to E-alerts

Indexed In


		AGRIS
		ASCI-Database
		Asian Digital Library
		Chemical Abstract Services
		Google Scholar

Science Alert