A hybrid linear/nonlinear training algorithm for feedforward neural networks

Authors:
S. McLoone;M. D. Brown;G. Irwin;A. Lightbody
Affiliations:
Dept. of Electr. & Electron. Eng., Queen's Univ., Belfast;-;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
1998

Citing 0
Cited 18

A new fuzzy neural network with fast learning algorithm and guaranteed stability for manufacturing process control

Fuzzy Sets and Systems - Fuzzy systems
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
Prediction- and simulation-error based perceptron training: Solution space analysis and a novel combined training scheme

Neurocomputing
Computational intelligence approaches and linear models in case studies of forecasting exchange rates

Expert Systems with Applications: An International Journal
Generalized multiscale radial basis function networks

Neural Networks
An Empirical Comparison of Training Algorithms for Radial Basis Functions

IWANN '03 Proceedings of the 7th International Work-Conference on Artificial and Natural Neural Networks: Part II: Artificial Neural Nets Problem Solving Methods
Model-free adaptive control design using evolutionary-neural compensator

Expert Systems with Applications: An International Journal
Construction of tunable radial basis function networks using orthogonal forward selection

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Two-stage mixed discrete-continuous identification of radial basis function (RBF) neural models for nonlinear systems

IEEE Transactions on Circuits and Systems Part I: Regular Papers
Non-linear system identification using particle swarm optimisation tuned radial basis function models

International Journal of Bio-Inspired Computation
Particle swarm optimization aided orthogonal forward regression for unified data modeling

IEEE Transactions on Evolutionary Computation
Fast forward RBF network construction based on particle swarm optimization

LSMS/ICSEE'10 Proceedings of the 2010 international conference on Life system modeling and simulation and intelligent computing, and 2010 international conference on Intelligent computing for sustainable energy and environment: Part II
Review article: A self-organizing map-based initialization for hybrid training of feedforward neural networks

Applied Soft Computing
A global-local optimization approach to parameter estimation of RBF-type models

Information Sciences: an International Journal
A two-stage algorithm for identification of nonlinear dynamic systems

Automatica (Journal of IFAC)
Letters: Random optimized geometric ensembles

Neurocomputing
Fast image classification algorithms based on random weights networks

ISNN'13 Proceedings of the 10th international conference on Advances in Neural Networks - Volume Part I
Sparse algorithms of Random Weight Networks and applications

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper presents a new hybrid optimization strategy for training feedforward neural networks. The algorithm combines gradient-based optimization of nonlinear weights with singular value decomposition (SVD) computation of linear weights in one integrated routine. It is described for the multilayer perceptron (MLP) and radial basis function (RBF) networks and then extended to the local model network (LMN), a new feedforward structure in which a global nonlinear model is constructed from a set of locally valid submodels. Simulation results are presented demonstrating the superiority of the new hybrid training scheme compared to second-order gradient methods. It is particularly effective for the LMN architecture where the linear to nonlinear parameter ratio is large