Numerical bounds to assure initial local stability of NARX multilayer perceptrons and radial basis functions

Authors:
Eloy Irigoyen;Miguel Pinzolas
Affiliations:
Department of System Engineering and Automation, University of the Basque Country, Alda, Urquijo s/n, E-48013 Bilbao, Vizcaya, Spain;Department of Systems Engineering and Automation, Technical University of Cartagena, Campus Muralla del Mar s/n, E-30202 Cartagena, Murcia, Spain
Venue:
Neurocomputing
Year:
2008

Citing 10
Cited 2

Initializing back propagation networks with prototypes

Neural Networks
Weight Initialization for Simultaneous Recurrent Neural Network Trained with a Fixed-point Learning Algorithm

Neural Processing Letters
Neural Networks for Constrained Optimal Control of Non-Linear Systems

IJCNN '00 Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks (IJCNN'00)-Volume 4 - Volume 4
Computational capabilities of recurrent NARX neural networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Learning long-term dependencies in NARX recurrent neural networks

IEEE Transactions on Neural Networks
High-order and multilayer perceptron initialization

IEEE Transactions on Neural Networks
New results on recurrent network training: unifying the algorithms and accelerating convergence

IEEE Transactions on Neural Networks
Identification and control of dynamical systems using neural networks

IEEE Transactions on Neural Networks
Linear-least-squares initialization of multilayer perceptrons through backpropagation of the desired response

IEEE Transactions on Neural Networks
On the initialization and optimization of multilayer perceptrons

IEEE Transactions on Neural Networks

Adding nonlinear system dynamics to Levenberg-Marquardt algorithm for neural network control

ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
A NARX neural network model for enhancing cardiovascular rehabilitation therapies

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this work, local stability on the initialization phase of nonlinear autoregressive with exogenous inputs multilayer perceptrons (NARX MLP) and radial basis functions (NARX RBF) neural networks is studied. It will be shown that the selection of adequate ranges for the initial weights is related with local stability of the network in its initial stage. As a result, quantitative limits for the initial weights are established that guarantee local stability and accelerate the learning process. These theoretical developments have been tested in experiments which corroborate the improvements achieved with the proposed initialization methods.