LMI formulation for multiobjective learning in radial basis function neural networks

Gladston J.P. Moreira, Elizabeth F. Wanner, Frederico G. Guimarães, Luiz H. Duczmal, Ricardo H.C. Takahashi

Research output: Chapter in Book/Published conference outputConference publication

Abstract

This work presents a Linear Matrix Inequality (LMI) formulation for training Radial Basis Function (RBF) neural networks, considering the context of multiobjective learning. The multiobjective learning approach treats the bias-variance dilemma in neural network modeling as a bi-objective optimization problem: the minimization of the empirical risk measured by the sum of squared error over the training data, and the minimization of the structure complexity measured by the norm of the weight vector. We transform the multiobjective problem into a constrained mono-objective one, using the ε-constraint method. This mono-objective problem can be efficiently solved using an LMI formulation. A procedure for choosing the width parameter of the radial basis functions is also presented. The results show that the proposed methodology provides generalization control and high quality solutions.

Original languageEnglish
Title of host publication2010 IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
DOIs
Publication statusPublished - 14 Oct 2010
Event2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010 - Barcelona, Spain
Duration: 18 Jul 201023 Jul 2010

Publication series

NameProceedings of the International Joint Conference on Neural Networks

Conference

Conference2010 6th IEEE World Congress on Computational Intelligence, WCCI 2010 - 2010 International Joint Conference on Neural Networks, IJCNN 2010
Country/TerritorySpain
CityBarcelona
Period18/07/1023/07/10

Fingerprint

Dive into the research topics of 'LMI formulation for multiobjective learning in radial basis function neural networks'. Together they form a unique fingerprint.

Cite this