DocumentCode :
2361563
Title :
Representation of complex-valued neural networks: a real-valued approach
Author :
Yadav, A. ; Mishra, D. ; Ray, S. ; Yadav, R.N. ; Kalra, P.K.
Author_Institution :
Dept. of Electr. Eng., Indian Inst. of Technol., Kanpur, India
fYear :
2005
fDate :
4-7 Jan. 2005
Firstpage :
331
Lastpage :
335
Abstract :
A methodology for representing a complex-valued multilayer artificial neural network and its backpropagation learning algorithm in terms of real-valued neural network has been discussed. The performance of the proposed method has been tested on complex-valued XOR problem and power system load flow problems.
Keywords :
backpropagation; feedforward neural nets; load distribution; multilayer perceptrons; XOR problem; backpropagation learning algorithm; complex nonlinear bounded activation function; complex-valued multilayer artificial neural network; power system load flow problem; Artificial neural networks; Backpropagation; Circuits; Load flow; Multi-layer neural network; Neural networks; Neurons; Power systems; Remote sensing; System testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Intelligent Sensing and Information Processing, 2005. Proceedings of 2005 International Conference on
Print_ISBN :
0-7803-8840-2
Type :
conf
DOI :
10.1109/ICISIP.2005.1529471
Filename :
1529471
Link To Document :
بازگشت