Please use this identifier to cite or link to this item:
https://ruomo.lib.uom.gr/handle/7000/491
Title: | An adaptive learning rate backpropagation-type neural network for solvingn×nsystems on nonlinear algebraic equations |
Authors: | Goulianas, Konstantinos Margaris, Athanasios Refanidis, Ioannis Diamantaras, Konstantinos I. |
Type: | Article |
Subjects: | FRASCATI::Natural sciences::Computer and information sciences |
Keywords: | non-linear algebraic systems backpropagation numerical analysis subclass 65H10 |
Issue Date: | 2016 |
Publisher: | Wiley |
Source: | Mathematical Methods in the Applied Sciences |
Volume: | 39 |
Issue: | 10 |
First Page: | 2602 |
Last Page: | 2616 |
Abstract: | This paper presents an MLP‐type neural network with some fixed connections and a backpropagation‐type training algorithm that identifies the full set of solutions of a complete system of nonlinear algebraic equations with n equations and n unknowns. The proposed structure is based on a backpropagation‐type algorithm with bias units in output neurons layer. Its novelty and innovation with respect to similar structures is the use of the hyperbolic tangent output function associated with an interesting feature, the use of adaptive learning rate for the neurons of the second hidden layer, a feature that adds a high degree of flexibility and parameter tuning during the network training stage. The paper presents the theoretical aspects for this approach as well as a set of experimental results that justify the necessity of such an architecture and evaluate its performance. |
URI: | https://doi.org/10.1002/mma.3715 https://ruomo.lib.uom.gr/handle/7000/491 |
ISSN: | 0170-4214 |
Electronic ISSN: | 1099-1476 |
Other Identifiers: | 10.1002/mma.3715 |
Appears in Collections: | Department of Applied Informatics |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
nonlinear-nxn-17.pdf | pre-print | 225,1 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.