A fully complex-valued radial basis function classifier for real-valued classification problems

In this paper, we investigate the decision making ability of a fully complex-valued radial basis function (FC-RBF) network in solving real-valued classification problems. The FC-RBF classifier is a single hidden layer fully complex-valued neural network with a nonlinear input layer, a nonlinear hidd...

Full description

Saved in:
Bibliographic Details
Main Authors: Suresh, Sundaram, Sundararajan, Narasimhan, Savitha, R., Kim, H. J.
Other Authors: School of Computer Engineering
Format: Article
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/99595
http://hdl.handle.net/10220/13650
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-99595
record_format dspace
spelling sg-ntu-dr.10356-995952020-05-28T07:17:46Z A fully complex-valued radial basis function classifier for real-valued classification problems Suresh, Sundaram Sundararajan, Narasimhan Savitha, R. Kim, H. J. School of Computer Engineering DRNTU::Engineering::Computer science and engineering In this paper, we investigate the decision making ability of a fully complex-valued radial basis function (FC-RBF) network in solving real-valued classification problems. The FC-RBF classifier is a single hidden layer fully complex-valued neural network with a nonlinear input layer, a nonlinear hidden layer, and a linear output layer. The neurons in the input layer of the classifier employ the phase encoded transformation to map the input features from the Real domain to the Complex domain. The neurons in the hidden layer employ a fully complex-valued Gaussian-like activation function of the type of hyperbolic secant (sech). The classification ability of the classifier is first studied analytically and it is shown that the decision boundaries of the FC-RBF classifier are orthogonal to each other. Then, the performance of the FC-RBF classifier is studied experimentally using a set of real-valued benchmark problems and also a real-world problem. The study clearly indicates the superior classification ability of the FC-RBF classifier. 2013-09-24T07:07:54Z 2019-12-06T20:09:21Z 2013-09-24T07:07:54Z 2019-12-06T20:09:21Z 2011 2011 Journal Article Savitha, R., Suresh, S., Sundararajan, N., & Kim, H. J. (2011). A fully complex-valued radial basis function classifier for real-valued classification problems. Neurocomputing, 78(1), 104-110. https://hdl.handle.net/10356/99595 http://hdl.handle.net/10220/13650 10.1016/j.neucom.2011.05.036 en Neurocomputing
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Suresh, Sundaram
Sundararajan, Narasimhan
Savitha, R.
Kim, H. J.
A fully complex-valued radial basis function classifier for real-valued classification problems
description In this paper, we investigate the decision making ability of a fully complex-valued radial basis function (FC-RBF) network in solving real-valued classification problems. The FC-RBF classifier is a single hidden layer fully complex-valued neural network with a nonlinear input layer, a nonlinear hidden layer, and a linear output layer. The neurons in the input layer of the classifier employ the phase encoded transformation to map the input features from the Real domain to the Complex domain. The neurons in the hidden layer employ a fully complex-valued Gaussian-like activation function of the type of hyperbolic secant (sech). The classification ability of the classifier is first studied analytically and it is shown that the decision boundaries of the FC-RBF classifier are orthogonal to each other. Then, the performance of the FC-RBF classifier is studied experimentally using a set of real-valued benchmark problems and also a real-world problem. The study clearly indicates the superior classification ability of the FC-RBF classifier.
author2 School of Computer Engineering
author_facet School of Computer Engineering
Suresh, Sundaram
Sundararajan, Narasimhan
Savitha, R.
Kim, H. J.
format Article
author Suresh, Sundaram
Sundararajan, Narasimhan
Savitha, R.
Kim, H. J.
author_sort Suresh, Sundaram
title A fully complex-valued radial basis function classifier for real-valued classification problems
title_short A fully complex-valued radial basis function classifier for real-valued classification problems
title_full A fully complex-valued radial basis function classifier for real-valued classification problems
title_fullStr A fully complex-valued radial basis function classifier for real-valued classification problems
title_full_unstemmed A fully complex-valued radial basis function classifier for real-valued classification problems
title_sort fully complex-valued radial basis function classifier for real-valued classification problems
publishDate 2013
url https://hdl.handle.net/10356/99595
http://hdl.handle.net/10220/13650
_version_ 1681058822968311808