Generalization characteristics of complex-valued feedforward neural networks in relation to signal coherence

IEEE Transactions on Neural Networks and Learning Systems

Volumn 23, Issue 4, 2012, Pages 541-551

  Hirose, Akira ^a   Yoshida, Shotaro ^a  

^a UNIVERSITY OF TOKYO   (Japan)

Author keywords

Complex valued neural network; function approximation; generalization; supervised learning

Indexed keywords

COHERENT IMAGING SYSTEMS; COMPLEX-VALUED FEEDFORWARD NEURAL NETWORKS; COMPLEX-VALUED NEURAL NETWORKS; FUNCTION APPROXIMATION; GENERALIZATION; GENERALIZATION ABILITY; GENERALIZATION ERROR; REAL WORLD EXPERIMENT;

COMPUTER SIMULATION; FEEDFORWARD NEURAL NETWORKS; SUPERVISED LEARNING;

COMPLEX NETWORKS;

ALGORITHM; ARTIFICIAL NEURAL NETWORK; AUTOMATED PATTERN RECOGNITION; COMPUTER ASSISTED DIAGNOSIS; COMPUTER SIMULATION; FEEDBACK SYSTEM; OPTICAL COHERENCE TOMOGRAPHY; PROCEDURES; STATISTICAL MODEL;

ALGORITHMS; COMPUTER SIMULATION; FEEDBACK; IMAGE INTERPRETATION, COMPUTER-ASSISTED; MODELS, STATISTICAL; NEURAL NETWORKS (COMPUTER); PATTERN RECOGNITION, AUTOMATED; TOMOGRAPHY, OPTICAL COHERENCE;

EID: 84859797266     PISSN: 2162237X     EISSN: 21622388     Source Type: Journal    
DOI: 10.1109/TNNLS.2012.2183613     Document Type: Article

References (26)

1. D. L. Birx and S. J. Pipenberg, "A complex mapping network for phase sensitive classification," IEEE Trans. Neural Netw., vol. 4, no. 1, pp. 127-135, Jan. 1993.
2. T. Hara and A. Hirose, "Plastic mine detecting radar system using complex-valued self-organizing map that deals with multiple-frequency interferometric images," Neural Netw., vol. 17, nos. 8-9, pp. 1201-1210, 2004.
3. S. Masuyama and A. Hirose, "Walled LTSA array for rapid, high spatial resolution, and phase-sensitive imaging to visualize plastic landmines," IEEE Trans. Geosci. Remote Sens., vol. 45, no. 8, pp. 2536-2543, Aug. 2007.
4. I. Aizenberg, D. V. Paliy, J. M. Zurada, and J. T. Astola, "Blur identification by multilayer neural network based on multivalued neurons," IEEE Trans. Neural Netw., vol. 19, no. 5, pp. 883-898, May 2008.
5. G. Tanaka and K. Aihara, "Complex-valued multistate associative memory with nonlinear multilevel functions for gray-level image reconstruction," IEEE Trans. Neural Netw., vol. 20, no. 9, pp. 1463-1473, Sep. 2009.
6. Y. Zhang and Y. Ma, "CGHA for principal component extraction in the complex domain," IEEE Trans. Neural Netw., vol. 8, no. 5, pp. 1031-1036, Sep. 1997.
7. H. Sawada, R. Mukai, S. Araki, and S. Makino, "Polar coordinate based nonlinear function for frequency-domain blind source separation," IEICE Trans. Fundam. Electron., Commun., Comput. Sci., vol. E86A, no. 3, pp. 590-596, 2003.
8. S. Goh and D. P. Mandic, "Nonlinear adaptive prediction of complexvalued signals by complex-valued PRNN," IEEE Trans. Signal Process., vol. 53, no. 5, pp. 1827-1836, May 2005.
9. A. Hirose and R. Eckmiller, "Behavior control of coherent-type neural networks by carrier-frequency modulation," IEEE Trans. Neural Netw., vol. 7, no. 4, pp. 1032-1034, Jul. 1996.
10. A. B. Suksmono and A. Hirose, "Beamforming of ultrawideband pulses by a complex-valued spatio-temporal multilayer neural network," Int. J. Neural Syst., vol. 15, no. 1, pp. 1-7, 2005.
11. A. Hirose, "Applications of complex-valued neural networks to coherent optical computing using phase-sensitive detection scheme," Inf. Sci.-Appl., vol. 2, no. 2, pp. 103-117, Sep. 1994.
12. S. Kawata and A. Hirose, "A coherent optical neural network that learns desirable phase values in frequency domain by using multiple opticalpath differences," Opt. Lett., vol. 28, no. 24, pp. 2524-2526, 2003.
13. A. Hirose, T. Higo, and K. Tanizawa, "Efficient generation of holographic movies with frame interpolation using a coherent neural network," IEICE Electron. Exp., vol. 3, no. 19, pp. 417-423, 2006.
14. Y. Nakamiya, M. Kinjo, O. Takahashi, S. Sato, and K. Nakajima, "Quantum neural network composed of Kane's qubits," Jpn. J. Appl. Phys., vol. 45, no. 10A, pp. 8030-8034, Oct. 2006.
15. A. Hirose, Y. Asano, and T. Hamano, "Developmental learning with behavioral mode tuning by carrier-frequency modulation in coherent neural networks," IEEE Trans. Neural Netw., vol. 17, no. 6, pp. 1532-1543, Nov. 2006.
16. H. Leung and S. Haykin, "The complex backpropagation algorithm," IEEE Trans. Signal Process., vol. 39, no. 9, pp. 2101-2104, Sep. 1991.
17. N. Benvenuto and F. Piazza, "On the complex backpropagation algorithm," IEEE Trans. Signal Process., vol. 40, no. 4, pp. 967-969, Apr. 1992.
18. T. Nitta, "An extension of the back-propagation algorithm to complex numbers," Neural Netw., vol. 10, no. 8, pp. 1391-1415, Nov. 1997.
19. A. Hirose, "Continuous complex-valued back-propagation learning," Electron. Lett., vol. 28, no. 20, pp. 1854-1855, 1992.
20. G. M. Georgiou and C. Koutsougeras, "Complex domain backpropagation," IEEE Trans. Circuits Syst. II, vol. 39, no. 5, pp. 330-334, May 1992.
21. A. Hirose, "Nature of complex number and complex-valued neural networks," Front. Electr. Electron. Eng. China, vol. 6, no. 1, pp. 171-180, 2011.
22. A. Hirose, Complex-Valued Neural Networks. New York: Springer-Verlag, 2006.
23. B. Picinbono and P. Chevalier, "Widely linear estimation with complex data," IEEE Trans. Signal Process., vol. 43, no. 8, pp. 2030-2033, Aug. 1995.
24. D. P. Mandic and V. S. L. Goh, Complex Valued Nonlinear Adaptive Filters-Noncircularity, Widely Linear and Neural Models. New York: Wiley, Apr. 2009.
25. Y. Xia, B. Jelfs, M. M. Van Hulle, J. C. Principe, and D. P. Mandic, "An augumented echo state network for nonlinear adaptive filetering of complex noncircular signals," IEEE Trans. Neural Netw., vol. 22, no. 1, pp. 74-83, Jan. 2011.
26. D. P. Mandic, S. Still, and S. C. Douglas, "Duality between widely linear and dual channel adaptive filtering," in Proc. IEEE Int. Conf. Acoust., Speech, Signal Process., Taipei, Taiwan, Apr. 2009, pp. 1729-1732.