A new EM-based training algorithm for RBF networks

Authors:
Marcelino Lázaro;Ignacio Santamaría;Carlos Pantaleón
Affiliations:
Departamento Ingeniería de Comunicaciones, ETSIIT, Universidad de Cantabria, Av. Los Castros s/n, 39005 Santander, Spain;Departamento Ingeniería de Comunicaciones, ETSIIT, Universidad de Cantabria, Av. Los Castros s/n, 39005 Santander, Spain;Departamento Ingeniería de Comunicaciones, ETSIIT, Universidad de Cantabria, Av. Los Castros s/n, 39005 Santander, Spain
Venue:
Neural Networks
Year:
2003

Citing 6
Cited 11

Hierarchical mixtures of experts and the EM algorithm

Neural Computation
Neural networks for pattern recognition

Neural networks for pattern recognition
An efficient EM-based training algorithm for feedforward neural networks

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Comparison of adaptive methods for function estimation from samples

IEEE Transactions on Neural Networks
Fast training of recurrent networks based on the EM algorithm

IEEE Transactions on Neural Networks

On the Kernel Widths in Radial-Basis Function Networks

Neural Processing Letters
Improvement of learning algorithms for RBF neural networks in a helicopter sound identification system

Neurocomputing
Generalized multiscale radial basis function networks

Neural Networks
A Fuzzy Clustering Algorithm to Estimate the Parameters of Radial Basis Functions Neural Networks and Its Application to System Modeling

SETN '08 Proceedings of the 5th Hellenic conference on Artificial Intelligence: Theories, Models and Applications
An experimental study of the extended NRBF regression model and its enhancement for classification problem

Neurocomputing
A study on the use of imputation methods for experimentation with Radial Basis Function Network classifiers handling missing attribute values: The good synergy between RBFNs and EventCovering method

Neural Networks
Kernel Width Optimization for Faulty RBF Neural Networks with Multi-node Open Fault

Neural Processing Letters
A neural network of smooth hinge functions

IEEE Transactions on Neural Networks
Sparse RBF Networks with Multi-kernels

Neural Processing Letters
A Radial Basis Function network training algorithm using a non-symmetric partition of the input space - Application to a Model Predictive Control configuration

Advances in Engineering Software
A growing and pruning sequential learning algorithm of hyper basis function neural network for function approximation

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a new Expectation-Maximization (EM) algorithm which speeds up the training of feedforward networks with local activation functions such as the Radial Basis Function (RBF) network. In previously proposed approaches, at each E-step the residual is decomposed equally among the units or proportionally to the weights of the output layer. However, these approaches tend to slow down the training of networks with local activation units. To overcome this drawback in this paper we use a new E-step which applies a soft decomposition of the residual among the units. In particular, the decoupling variables are estimated as the posterior probability of a component given an input-output pattern. This adaptive decomposition takes into account the local nature of the activation function and, by allowing the RBF units to focus on different subregions of the input space, the convergence is improved. The proposed EM training algorithm has been applied to the nonlinear modeling of a MESFET transistor.