Deterministic Annealing Learning of the Radial Basis Function Nets for Improving the Regression Ability of RBF Network

I
IJCNN
2000
IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3
Abstract - Deterministic Annealing Learning of the Radial Basis Function Nets for Improving the Regression Ability of RBF Network

	This Article
	Subscribers, please Login Purchase article: $19 PDF IEEE Xplore Subscribers RSS feed
	Share
	Email this Article to a friend
	Bibliographic References
	ASCII Text BibTex RefWorks Procite/RefMan
	Add to:
	Digg Furl Spurl Blink Simpy Google Del.icio.us Y!MyWeb
	Search
	Similar Articles Articles by Nanning Zheng Articles by Zhihua Zhang Articles by Haibing Zheng Articles by Shi Gang

IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3

Como, Italy

July 24-July 27

ISBN: 0-7695-0619-4

	ASCII Text	x
	Nanning Zheng, Zhihua Zhang, Haibing Zheng, Shi Gang, "Deterministic Annealing Learning of the Radial Basis Function Nets for Improving the Regression Ability of RBF Network," Neural Networks, IEEE - INNS - ENNS International Joint Conference on, vol. 3, pp. 3601, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3, 2000.

	BibTex	x
	@article{ 10.1109/IJCNN.2000.861384, author = {Nanning Zheng and Zhihua Zhang and Haibing Zheng and Shi Gang}, title = {Deterministic Annealing Learning of the Radial Basis Function Nets for Improving the Regression Ability of RBF Network}, journal ={Neural Networks, IEEE - INNS - ENNS International Joint Conference on}, volume = {3}, year = {2000}, issn = {1098-7576}, pages = {3601}, doi = {http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.861384}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, }

	RefWorks Procite/RefMan/Endnote	x
	TY - CONF JO - Neural Networks, IEEE - INNS - ENNS International Joint Conference on TI - Deterministic Annealing Learning of the Radial Basis Function Nets for Improving the Regression Ability of RBF Network SN - 1098-7576 SP EP A1 - Nanning Zheng, A1 - Zhihua Zhang, A1 - Haibing Zheng, A1 - Shi Gang, PY - 2000 KW - Radial basis function net KW - deterministic annealing KW - Lagrangian Multiplier VL - 3 JA - Neural Networks, IEEE - INNS - ENNS International Joint Conference on ER -

Nanning Zheng, Xi'an Jiaotong University

Zhihua Zhang, Xi'an Jiaotong University

Haibing Zheng, Xi'an Jiaotong University

Shi Gang, Xi'an Jiaotong University

DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/IJCNN.2000.861384

In this paper, the deterministic annealing method for training the center vectors of RBF network is proposed. The method is a soft-competition scheme and derived from optimizing an objective function using the gradient descent method. To some extent, it can overcome the problems that the learning vector quantization algorithms with the winner-take-all scheme and the heuristic procedure have. The emulation experiment is given to validate the algorithm. The experimental results show that, compared the error back-propagating algorithms of the multi-layer perception and the RBF network, it not only enhances learning precision and generalization ability, but also reduces learning time as well.

Index Terms:

Radial basis function net, deterministic annealing, Lagrangian Multiplier

Citation:

Nanning Zheng, Zhihua Zhang, Haibing Zheng, Shi Gang, "Deterministic Annealing Learning of the Radial Basis Function Nets for Improving the Regression Ability of RBF Network," ijcnn, vol. 3, pp.3601, IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 3, 2000

Peer Review Notice | Give Us Feedback

Usage of this product signifies your acceptance of the Terms of Use.