Title :
Hermite neural network correlation and application
Author :
Mackenzie, Mark R. ; Tieu, A. Kiet
Author_Institution :
Sch. of Mech., Univ. of Wollongong, Australia
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;
Journal_Title :
Signal Processing, IEEE Transactions on
DOI :
10.1109/TSP.2003.819005
