DocumentCode
3441762
Title
Neural networks for quaternion-valued function approximation
Author
Arena, P. ; Fortuna, L. ; Occhipinti, L. ; Xibilia, M.G.
Author_Institution
Dept. Elettrotecnica Elettronica e Sistemistico, Catania Univ., Italy
Volume
6
fYear
1994
fDate
30 May-2 Jun 1994
Firstpage
307
Abstract
In the paper a new structure of a Multi-Layer Perceptron, able to deal with quaternion-valued signals, is proposed. A learning algorithm for the proposed Quaternion MLP (QMLP) is also derived. Such a neural network allows one to interpolate functions of a quaternion variable with a smaller number of connections with respect to the corresponding real valued MLP
Keywords
function approximation; interpolation; learning (artificial intelligence); multilayer perceptrons; QMLP; function approximation; interpolation; learning algorithm; multi-layer perceptron; neural networks; quaternion-valued signals; Algebra; Computational complexity; Feedforward systems; Function approximation; Interpolation; Multilayer perceptrons; Neural networks; Neurons; Physics; Quaternions;
fLanguage
English
Publisher
ieee
Conference_Titel
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location
London
Print_ISBN
0-7803-1915-X
Type
conf
DOI
10.1109/ISCAS.1994.409587
Filename
409587
Link To Document