Title :
Convergence of Hopfield neural network for orthogonal transformation
Author :
Kamio, Takeshi ; Ninomiya, Hiroshi ; Asai, Hideki
Author_Institution :
Fac. of Eng., Shizuoka Univ., Hamamatsu, Japan
fDate :
30 Apr-3 May 1995
Abstract :
In this paper, we describe the convergence of the discrete Walsh transform (DWT) processor based on Hopfield neural networks. First, the influence of the orthonormal matrix on solving linear equations by the steepest descent (SD) method is investigated and this theory is applied to the convergence of Hopfield neural networks. Finally, it is shown both analytically and by simulation that this type of network is suitable for orthogonal transforms
Keywords :
Hopfield neural nets; Walsh functions; convergence of numerical methods; equations; matrix algebra; transforms; Hopfield neural network; convergence; discrete Walsh transform processor; linear equations; orthogonal transformation; orthonormal matrix; simulation; steepest descent method; Application software; Convergence; Discrete transforms; Discrete wavelet transforms; Equations; Hopfield neural networks; Neural networks; Signal processing; Symmetric matrices; Vectors;
Conference_Titel :
Circuits and Systems, 1995. ISCAS '95., 1995 IEEE International Symposium on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-2570-2
DOI :
10.1109/ISCAS.1995.521558
