A modified error backpropagation algorithm for complex-value neural networks

International Journal of Neural Systems

Volumn 15, Issue 6, 2005, Pages 435-443

  Chen, Xiaoming ^a   Tang, Zheng ^a   Variappan, Catherine ^a   Li, Songsong ^b   Okada, Toshimi ^b  

^a UNIVERSITY OF TOYAMA   (Japan)

^b TOYAMA PREFECTURAL UNIVERSITY   (Japan)

Author keywords

Backpropagation; Complex value network; Local minima; Modified error function

Indexed keywords

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; ARTIFICIAL NEURAL NETWORK; COMPUTER SIMULATION; LEARNING; MATHEMATICS; SIGNAL PROCESSING;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; COMPUTER SIMULATION; LEARNING; MATHEMATICS; NEURAL NETWORKS (COMPUTER); SIGNAL PROCESSING, COMPUTER-ASSISTED;

EID: 33644877879     PISSN: 01290657     EISSN: None     Source Type: Journal    
DOI: 10.1142/S0129065705000426     Document Type: Article

References (16)

1. N. Benven and F. Piazza, On the complex backpropagation algorithm, IEEE Trans. on Signal Processing 40 (1992) 967-969.
2. G. M. Georgio and C. Koutsougeras, Complex domain backpropagation, IEEE Trans. on Circuits. Syst-II: Analog Digital Signal Processing 39 (1992) 330-334.
3. M. S. Kim and C. C. Guest, Modification of backpropagation networks for complex-valued signal processing in frequency domain, in Proc. Internat. Joint Conf. Neural Networks 3 (1990) 27-31.
4. T. Nitta and T. Furuya, A complex backpropagation learning, Trans. of Information Processing Society of Japan 32 (1991) 1319-1329.
5. T. Nitta, An extension of the back-propagation algorithm to complex numbers, Neural Networks 10 (1997) 1391-1415.
6. T. Nitta, Solving the XOR problem and the detection of symmetry using a single complex-valued neuron, Neural Networks 16 (2003) 1101-1105.
7. A. Von Lehmen, E. G. Paek, P. F. Liao, A. Marrakchi and J. S. Patel, Factors influencing learning by backpropagation, in Proc. IEEE Int. Conf. Neural Networks I (1988) 335-341.
8. C. B. Owen and A. M. Abunawass, Application of simulated annealing to the backpropagation model improves convergence, in Proc. SPICE Conf. Science of Artifical Neural Networks II (1993) 269-276.
9. C. Wang and J. C. Principe, Training neural networks with additive noise in the desired signal, IEEE Trans. on Neural Networks 10 (1999) 1511-1517.
10. A. Hadjiprocopis, Feed forward neural network entities, Ph.D. thesis, Department of Computer Science, City University, UK (2000).
11. G. Goerick and W. V. Seelen, On unlearnable problems or a model for premature saturation in backpropagation learning, in Proc. of the European Symposium on Artifical Neural Networks (1996) 13-18.
12. S. Haykin, Neural Networks a Comprehensive Foundation (Macmillan Publishing, New York, 1994).
13. X. G. Wang and Z. Tang, A modified error function for the backpropagation algorithm, Neurocomputing 57 (2004) 477-484.
14. G. Cybenko, Approximation by superposition of a sigmoid function, Mathematics of Control, Signals, and Systems 2 (1989) 303-314.
15. T. Kim and T. Adali, Fully complex multi-layer perceptron network for nonlinear signal processing, J. VLSI Signal Processing Systems for Signal, Image, and Video Technology, Special Issue: Neural Networks for Signal Processing 32 (2002) 29-43.
16. T. Kim and T. Adali, Approximation by fully complex multilayer perceptions, Neural Computation 15 (2003) 1641-1666.