Training Radial Basis Functions by Gradient Descent

Lecture notes in computer sciencePublished 1 January 2004

Mercedes Fernández-Redondo, Carlos Hernández-Espinosa, Mamen Ortiz-Gómez, Joaquín Torres-Sospedra

DOI10.1007/978-3-540-24844-6_23

Source URL

Citations8

SJR quartileQ2

SJR score0.35

SNIP0.55

TL;DR

This paper presents experiments comparing different training algorithms for Radial Basis Functions (RBF) neural networks and concludes that a fully supervised training performs generally better.

Abstract

In this paper we present experiments comparing different training algorithms for Radial Basis Functions (RBF) neural networks. In particular we compare the classical training which consist of a unsupervised training of centers followed by a supervised training of the weights at the output, with the full supervised training by gradient descent proposed recently in same papers. We conclude that a fully supervised training performs generally better. We also compare Batch training with Online training and we conclude that Online training suppose a reduction in the number of iterations.

Keywords

Computer SciencePhysics and Astronomy

Neural ComputationFast Learning in Networks of Locally-Tuned Processing Units

4,219 Citations1989John Moody, Christian J. Darken

This work proposes a network architecture which uses a single internal layer of locally-tuned processing units to learn both classification tasks and real-valued function approximations (Moody and Darken 1988).

IEEE Transactions on Neural NetworksReformulated radial basis neural networks trained by gradient descent

281 Citations1999N.B. Karayiannis

Experiments involving a variety of reformulated RBF networks generated by linear and exponential generator functions indicate that gradient descent learning is simple, easily implementable, and produces RBf networks that perform considerably better than conventional RBF models trained by existing algorithms.

Neural NetworksAn Efficient Method to Construct a Radial Basis Function Neural Network Classifier

163 Citations1997Young-Sup Hwang, Sung-Yang Bang

IEEE Transactions on Neural NetworksOn the construction and training of reformulated radial basis function neural networks

126 Citations2003N.B. Karayiannis, M.M. Randolph-Gips

Cosine radial basis functions are shown to be strong competitors to existing reformulated radial basis function models trained by gradient descent and feedforward neural networks with sigmoid hidden units.

Neural NetworksAn algorithm to generate radial basis function (RBF)-like nets for classification problems

120 Citations1995Asim Roy, Sandeep Govil +1 more

A new algorithm for generating radial basis function (RBF)-like nets for classification problems using linear programming models to train the RBF-like net is presented.

IEEE Transactions on Neural NetworksA neural-network learning theory and a polynomial time RBF algorithm

84 Citations1997Asim Roy, Sandeep Govil +1 more

A new learning theory (a set of principles for brain-like learning) and a corresponding algorithm for the neural-network field are presented and computational results are provided for the well known Mackey-Glass chaotic time series problem, the logistic map prediction problem, various neuro-control problems, and several time series forecasting problems.