Please use this identifier to cite or link to this item: https://ruomo.lib.uom.gr/handle/7000/499
Title: A Back Propagation-Type Neural Network Architecture for Solving the Complete nxn Nonlinear Algebraic System of Equations
Authors: Goulianas, Konstantinos
Margaris, Athanasios
Refanidis, Ioannis
Diamantaras, Konstantinos
Papadimitriou, Theofilos
Type: Article
Subjects: FRASCATI::Natural sciences::Mathematics
FRASCATI::Natural sciences::Computer and information sciences
Keywords: Nonlinear Algebraic Systems
Neural Networks
Back Propagation
Numerical Analysis
Computational Methods
Issue Date: 2016
Publisher: Scientific Research, Open access
Source: Advances in Pure Mathematics
Volume: 06
Issue: 06
First Page: 455
Last Page: 480
Abstract: The objective of this research is the presentation of a neural network capable of solving complete nonlinear algebraic systems of n equations with n unknowns. The proposed neural solver uses the classical back propagation algorithm with the identity function as the output function, and supports the feature of the adaptive learning rate for the neurons of the second hidden layer. The paper presents the fundamental theory associated with this approach as well as a set of experimental results that evaluate the performance and accuracy of the proposed method against other methods found in the literature.
URI: https://doi.org/10.4236/apm.2016.66033
https://ruomo.lib.uom.gr/handle/7000/499
ISSN: 2160-0368
Electronic ISSN: 2160-0384
Other Identifiers: 10.4236/apm.2016.66033
Appears in Collections:Department of Applied Informatics

Files in This Item:
File Description SizeFormat 
APM_2016053116554726.pdfpublisher version1,24 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.