File(s) not publicly available

The development of a nonlinear curve fitter using RBF neural networks with hybrid neurons

conference contribution
posted on 21.12.2017, 00:00 by Minmei Li
This paper investigates a new method using radial basis function (RBF) neu-ral networks with an additional linear neuron for solving nonlinear curve fit-ting problem. The complicated unknown function to be fitted is approximat-ed by a set of Gaussian basis function with a linear term correction. The proposed new technique is first used to evaluate two benchmark examples and subsequently applied to fit several heavy ion stopping power datasets (MeV energetic projectiles in aluminium). Due to the linear correction effect, the proposed approach significantly improves accuracy of fitting without adding much computational complexity. The developed method can be served as a standalone curve fitter or implemented as a proprietary software module to be embedded in an intelligent data analysis package for applica-tions in regression analysis.

History

Editor

Cheng L; Liu Q; Ronzhin A

Parent Title

Advances in neural networks -- ISNN 2016 : 13th International Symposium on Neural Networks, Proceedings

Start Page

434

End Page

443

Number of Pages

10

Start Date

06/07/2016

Finish Date

08/07/2016

eISSN

1611-3349

ISSN

0302-9743

ISBN-13

9783319406626

Location

St Petersburg, Russia

Publisher

Springer

Place of Publication

Cham, Switzerland

Peer Reviewed

Yes

Open Access

No

Author Research Institute

Centre for Intelligent Systems

Era Eligible

Yes

Name of Conference

International Symposium on Neural Networks, 13th, Isnn 2016

Exports

CQUniversity

Categories

Exports