DocumentCode :
1713537
Title :
Application of SFG in learning algorithms of neural networks
Author :
Osowski, Stanislaw ; Cichocki, Andrzej
Author_Institution :
Inst. of the Theory of Electr. Eng. & Electr. Meas., Tech. Univ. Warsaw, Poland
fYear :
1996
Firstpage :
75
Lastpage :
83
Abstract :
The paper presents the application of signal flow graphs (SFG) and adjoint flow graphs (AFG) in determination the gradient vector for feedforward neural networks. The presented approach is universal and applicable in the same form irrespective of the particular structure of the network. The applicability of the method has been shown on examples of different types of neural networks: multilayer perceptron, sigma-pi network, generalized radial basis network and multilayer Volterra network. The method finds application in any gradient based learning algorithms of neural networks. Some applications of this method, concerning the prediction and identification of the nonlinear dynamic plants are presented and discussed in the paper
Keywords :
feedforward neural nets; identification; multilayer perceptrons; signal flow graphs; adjoint flow graphs; feedforward neural networks; gradient vector; identification; learning algorithms; multilayer Volterra network; multilayer perceptron; nonlinear dynamical systems; radial basis function network; sigma-pi network; signal flow graphs; Artificial neural networks; Biological neural networks; Cost function; Feedforward neural networks; Feedforward systems; Flow graphs; Intelligent networks; Multi-layer neural network; Multilayer perceptrons; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks for Identification, Control, Robotics, and Signal/Image Processing, 1996. Proceedings., International Workshop on
Conference_Location :
Venice
Print_ISBN :
0-8186-7456-3
Type :
conf
DOI :
10.1109/NICRSP.1996.542747
Filename :
542747
Link To Document :
بازگشت