DocumentCode :
2612630
Title :
On the capability of neural networks with complex neurons in complex valued functions approximation
Author :
Arena, P. ; Fortuna, L. ; Re, R. ; Xibilia, M.G.
Author_Institution :
Univ. Degli Studi di Catania, Italy
fYear :
1993
fDate :
3-6 May 1993
Firstpage :
2168
Abstract :
The capability of neural networks with complex neurons to approximate complex valued functions is investigated. A density theorem for complex multilayer perceptrons (MLPs) with a nonanalytic activation function and one hidden layer is proved. The backpropagation algorithms for MLPs with real, complex analytic and complex non-analytic activation functions are compared with a numerical example
Keywords :
backpropagation; multilayer perceptrons; transfer functions; backpropagation algorithms; complex neurons; complex valued functions approximation; hidden layer; multilayer perceptrons; neural networks; nonanalytic activation function; Algorithm design and analysis; Approximation methods; Control theory; Function approximation; Intelligent networks; Linear approximation; Neural networks; Neurons; Radar signal processing; Signal processing algorithms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Circuits and Systems, 1993., ISCAS '93, 1993 IEEE International Symposium on
Conference_Location :
Chicago, IL
Print_ISBN :
0-7803-1281-3
Type :
conf
DOI :
10.1109/ISCAS.1993.394188
Filename :
394188
Link To Document :
بازگشت