DocumentCode
942932
Title
On the complex backpropagation algorithm
Author
Benvenuto, N. ; Piazza, F.
Author_Institution
Dipartimento di Elettronica ed Inf., Padova Univ., Italy
Volume
40
Issue
4
fYear
1992
fDate
4/1/1992 12:00:00 AM
Firstpage
967
Lastpage
969
Abstract
A recursive algorithm for updating the coefficients of a neural network structure for complex signals is presented. Various complex activation functions are considered and a practical definition is proposed. The method, associated to a mean-square-error criterion, yields the complex form of the conventional backpropagation algorithm
Keywords
neural nets; signal processing; coefficients updating; complex activation functions; complex backpropagation algorithm; complex signals; mean-square-error criterion; neural network; recursive algorithm; signal processing; Backpropagation algorithms; Equations; Multi-layer neural network; Multilayer perceptrons; Neural networks; Neurons; Nonlinear filters; Signal processing; Signal processing algorithms; Wiener filter;
fLanguage
English
Journal_Title
Signal Processing, IEEE Transactions on
Publisher
ieee
ISSN
1053-587X
Type
jour
DOI
10.1109/78.127967
Filename
127967
Link To Document