Convergent Decomposition Techniques for Training RBF Neural Networks

Authors:
C. Buzzi;L. Grippo;M. Sciandrone
Affiliations:
Dipartimento di Informatica e Sistemistica, Università di Roma "La Sapienza," Via Buonarroti 12 00185, Roma, Italy;Dipartimento di Informatica e Sistemistica, Università di Roma "La Sapienza," Via Buonarroti 12 00185, Roma, Italy;Istituto di Analisi dei Sistemi ed Informatica del CNR, Viale Manzoni 30-00185 Roma, Italy
Venue:
Neural Computation
Year:
2001

Citing 2
Cited 3

Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
On the convergence of the block nonlinear Gauss-Seidel method under convex constraints

Operations Research Letters

Learning Capability: Classical RBF Network vs. SVM with Gaussian Kernel

IEA/AIE '02 Proceedings of the 15th international conference on Industrial and engineering applications of artificial intelligence and expert systems: developments in applied artificial intelligence
Identification and modeling of nonlinear dynamical systems using a novel self-organizing RBF-based approach

Automatica (Journal of IFAC)
Canonical dual solutions to nonconvex radial basis neural network optimization problem

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article we define globally convergent decomposition algorithms for supervised training of generalized radial basis function neural networks. First, we consider training algorithms based on the two-block decomposition of the network parameters into the vector of weights and the vector of centers. Then we define a decomposition algorithm in which the selection of the center locations is split into sequential minimizations with respect to each center, and we give a suitable criterion for choosing the centers that must be updated at each step. We prove the global convergence of the proposed algorithms and report the computational results obtained for a set of test problems.