Learning method for neural networks using weight perturbation of orthogonal bit sequence and its application to adaptive WDM demultiplexer

Journal of Lightwave Technology

Volumn 15, Issue 11, 1997, Pages 1997-2004

  Aisawa, Shigeki ^a,b,c   Noguchi, Kazuhiro ^a   Miyao, Hiroshi ^a  

^a NTT CORPORATION   (Japan)

^b KANAZAWA UNIVERSITY   (Japan)

^c Institute of Electronics   (Japan)

Author keywords

Learning; Neural networks; Optical demultiplexer; Perturbation; Wavelength division multiplexing (WDM)

Indexed keywords

COMMUNICATION CHANNELS (INFORMATION THEORY); CORRELATION DETECTORS; ELECTRIC NETWORK PARAMETERS; ERROR CORRECTION; FREQUENCY DIVISION MULTIPLEXING; LEARNING SYSTEMS; OPTICAL COMMUNICATION; OPTICAL CORRELATION; OPTICAL FIBERS; PERTURBATION TECHNIQUES; SIGNAL DETECTION; TRANSMITTERS;

ADAPTIVE WAVELENGTH DIVISION MULTIPLEXER (WDM) DEMULTIPLEXERS; ORTHOGONAL BIT SEQUENCES;

NEURAL NETWORKS;

EID: 0031274925     PISSN: 07338724     EISSN: None     Source Type: Journal    
DOI: 10.1109/50.641517     Document Type: Article

References (15)

1. K. Yamada, H. Kami, J. Tsukumo, and T. Temma, "Handwritten neural recognition by multi-layered neural network with improved learning algorithm," in Proc. IJCNN'89, 1989, vol. II, pp. 259-266.
2. M. Kawato, Y. Uno, M. Isobe, and R. Suzuki, "A hierarchical model for voluntary movement and its application to robotics," in Proc. ICNN'87, 1987, vol. 4, pp. 573-582.
3. S. Aisawa, K. Noguchi, M. Koga, T. Matsumoto, Y. Amemiya, and A. Sugita, "Neural processing type optical WDM demultiplexer," IEEE J. Lightwave Technol., vol. 11, pp. 2130-2139, Dec. 1993.
4. S. Aisawa, K. Noguchi, T. Matsumoto, H. Tsunetsugu, and M. Yuda, "Neural processing type optical WDM demultiplexer using a grating," Trans. IEICE, vol. J78-B-I, no. 8, pp. 343-355, Aug. 1995.
5. S. Aisawa, K. Noguchi, M. Koga, T. Matsumoto, and Y. Amemiya, "Very-high-speed analog neural network LSI implementation using super self-aligned Si bipolar process technology," in Proc. IJCNN'93, Oct. 1993, vol. 1, pp. 895-898.
6. S. Aisawa, K. Noguchi, M. Koga, T. Matsumoto, and Y. Amemiya, "Very-high-speed analog neural network LSI using super self-aligned Si bipolar process technology," IEICE Trans. Electron., vol. E-77C, no. 6, pp. 1005-1008, June 1994.
7. H. Hikawa, "Implementation of simplified multilayer neural networks with on-chip learning," in Proc. ICNN'95, 1995, pp. 1633-1637.
8. T. Morie and Y. Amemiya, "An all-analog expandable neural network LSI with on-chip back-propagation learning," IEEE J. Solid-State Circuits, vol. 29, pp. 1086-1093, Sept. 1994.
9. T. Matsumoto and M. Koga, "Novel learning method for analog neural networks," Electron. Lett., vol. 26, no. 15, pp. 1136-1137, July 1990.
10. H. Miyao, M. Koga, and T. Matsumoto, "Hardware implementation of the multi-frequency learning method for analog neural networks," IEICE Trans. Inform. Syst., vol. E76-D, no. 6, pp. 717-719, June 1993.
11. T. Morie, O. Fujita, and Y. Amemiya, "Analog VLSI implementation of adaptive algorithms by an extended Hebbian learning," IEICE Trans. Electron., vol. E-75C, no. 3, pp. 303-311, Mar. 1992.
12. D. E. Rummerlhert, J. L. McCelland, and PDP Research group, Parallel Distributed Processing, vol. 1. Cambridge, MA: M.I.T. Press, 1986.
13. H. Miyakawa, Y. Iwatare, and H. Imai, Coding Theory. Syokoudou, 1973 (in Japanese).
14. Z. Kiyasu, "Hadamard matrix and its applications," IEICE, 1980, Chap. 16, pp. 449-472 (in Japanese).
15. O. Fujita and Y. Amemiya, "A floating gate analog memory device for neural networks," IEEE Trans. Electron. Devices, vol. 40, pp. 2029-2035, Nov. 1993.