Non uniform noisy data training using wavelet neural network based on sampling theory

Authors:
Ehsan Hossaini Asl;Mehdi Shahbazian;Karim Salahshoor
Affiliations:
Department of Automation and Instrumentation, Petroleum University of technology, Tehran, Iran;Department of Automation and Instrumentation, Petroleum University of technology, Tehran, Iran;Department of Automation and Instrumentation, Petroleum University of technology, Tehran, Iran
Venue:
WSEAS TRANSACTIONS on SYSTEMS
Year:
2008

Citing 5
Cited 0

A Theory for Multiresolution Signal Decomposition: The Wavelet Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning algorithm of wavelet network based on sampling theory

Neurocomputing
Function approximation using artificial neural networks

WSEAS Transactions on Mathematics
Wavelet neural networks for function learning

IEEE Transactions on Signal Processing
De-noising by soft-thresholding

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

Global convergence and overfitting are the main problem in neural network training. One of the new methods to overcome these problems is sampling theory that is applied in training of wavelet neural network. In this paper this new method is improved for training of wavelet neural network in non uniform and noisy data. The improvements include suggesting a method for finding the appropriate feedback matrix, addition of early stopping and wavelet thresholding to training procedure. Two experiments are conducted for one and two dimensional function. The results establish a satisfied performance of this algorithm in reduction of generalization error, reduction the complexity of wavelet neural network and mainly avoiding overfitting.