DocumentCode
831080
Title
Hermite neural network correlation and application
Author
Mackenzie, Mark R. ; Tieu, A. Kiet
Author_Institution
Sch. of Mech., Univ. of Wollongong, Australia
Volume
51
Issue
12
fYear
2003
Firstpage
3210
Lastpage
3219
Abstract
A method for obtaining the correlation of two Hermite neural networks is developed. The method is based on the fact that a Hermite function is unchanged by the Fourier transform, which allows an expression for the correlation to be obtained directly from the network weights without the need for the Fourier transform. Comparative results with other neural network correlation methods are presented on simulated radar signals.
Keywords
Fourier transforms; correlation methods; learning (artificial intelligence); neural nets; series (mathematics); signal processing; Fourier transform; Hermite function; Hermite neural network correlation; Hermite series expansion; neural network training; radar signals; signal processing; Biomedical engineering; Biomedical signal processing; Correlation; Doppler radar; Fourier transforms; Interpolation; Neural networks; Neurofeedback; Polynomials; Signal processing algorithms;
fLanguage
English
Journal_Title
Signal Processing, IEEE Transactions on
Publisher
ieee
ISSN
1053-587X
Type
jour
DOI
10.1109/TSP.2003.819005
Filename
1246527
Link To Document