Building RBF neural network topology through potential functions

Authors:
Natacha Gueorguieva;Iren Valova
Affiliations:
Computer Science, City University of New York, Staten Island, NY;Computer and Information Sciences, University of Massachusetts Dartmouth, N. Dartmouth, MA
Venue:
ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Year:
2003

Citing 8
Cited 2

Multilayer feedforward networks are universal approximators

Neural Networks
A Gaussian potential function network with hierarchically self-organizing learning

Neural Networks
Universal approximation using radial-basis-function networks

Neural Computation
Approximation and radial-basis-function networks

Neural Computation
Representing Probabilistic Rules with Networks of GaussianBasis Functions

Machine Learning
Fast learning in networks of locally-tuned processing units

Neural Computation
Median radial basis function neural network

IEEE Transactions on Neural Networks
Approximation capability to functions of several variables, nonlinear functionals, and operators by radial basis function neural networks

IEEE Transactions on Neural Networks

POFGEC: growing neural network of classifying potential function generators

International Journal of Knowledge Engineering and Soft Data Paradigms
Parameter estimation of q-Gaussian Radial Basis Functions Neural Networks with a Hybrid Algorithm for binary classification

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper we propose a strategy to shape adaptive radial basis functions through potential functions. DYPOF (DYnamic POtential Functions) neural network (NN) is designed based on radial basis functions (RBF) NN with a two-stage training procedure. Static (fixed number of RBF) and dynamic (ability to add or delete one or more RBF) versions of our learning algorithm are introduced. We investigate the change of cluster shape with the dimension of the input data, the choice of univariate potential function, and the construction of multivariate potential functions. Several data sets are considered to demonstrate the classification performance on the training and testing exemplars as well as compare DYPOF with other neural networks.