Complex domain backpropagation

作者: G.M. Georgiou , C. Koutsougeras

DOI: 10.1109/82.142037

关键词:

摘要: The backpropagation algorithm is extended to complex domain (CDBP) which can be used train neural networks for the inputs, weights, activation functions, and outputs are complex-valued. Previous derivations of CDBP were necessarily admitting functions that have singularities, highly undesirable. In derivation, derived so it accommodates classes suitable functions. One such function found circuit implementation corresponding neuron given. hardware circuits process sinusoidal signals all at same frequency (phasors). >

参考文章(7)
B. WIDROW, M. E. HOFF, Adaptive switching circuits Neurocomputing: foundations of research. pp. 123- 134 ,(1988) , 10.21236/AD0241531
M.S. Kim, C.C. Guest, Modification of backpropagation networks for complex-valued signal processing in frequency domain 1990 IJCNN International Joint Conference on Neural Networks. ,vol. 3, pp. 27- 31 ,(1990) , 10.1109/IJCNN.1990.137820
Bart Kosko, John C. Burgess, Neural networks and fuzzy systems Journal of the Acoustical Society of America. ,vol. 103, pp. 3131- 3131 ,(1998) , 10.1121/1.423096
H. Leung, S. Haykin, The complex backpropagation algorithm IEEE Transactions on Signal Processing. ,vol. 39, pp. 2101- 2104 ,(1991) , 10.1109/78.134446
M. Dentino, J. McCool, B. Widrow, Adaptive filtering in the frequency domain Proceedings of the IEEE. ,vol. 66, pp. 1658- 1659 ,(1978) , 10.1109/PROC.1978.11177
B. Widrow, J. McCool, M. Ball, The complex LMS algorithm Proceedings of the IEEE. ,vol. 63, pp. 719- 720 ,(1975) , 10.1109/PROC.1975.9807
D. E. Rumelhart, G. E. Hinton, R. J. Williams, Learning internal representations by error propagation Parallel distributed processing: explorations in the microstructure of cognition, vol. 1. ,vol. 1, pp. 318- 362 ,(1986)