Letters: Learning algorithm and hidden node selection scheme for local coupled feedforward neural network classifier

Authors:
Jianye Sun
Affiliations:
Computation Center, Harbin University of Science and Technology, No 52, Xuefu Road, PR China
Venue:
Neurocomputing
Year:
2012

Citing 7
Cited 0

Effective Data Mining Using Neural Networks

IEEE Transactions on Knowledge and Data Engineering
The CN2 Induction Algorithm

Machine Learning
Induction of Decision Trees

Machine Learning
Evolving an artificial neural network classifier for condition monitoring of rotating mechanical systems

Applied Soft Computing
A fusion neural network classifier for image classification

Pattern Recognition Letters
Local coupled feedforward neural network

Neural Networks
Neural networks for classification: a survey

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, a neural classifier based on the newly developed local coupled feedforward neural network, which may improve the convergence of BP learning significantly, is developed. A binary threshold unit is used as the output node of the classifier. A general error gradient of the output node is defined for the BP training of the classifier. And a hidden node selection scheme is developed for the local coupled feedforward neural network. In addition, we derive a result on the ''universal approximation'' property of the local coupled feedforward neural network with an arbitrary group of window functions, which can cover the region of training samples. Simulation results show that the general error gradient and the hidden node selection scheme work well.