Incorporation of liquid-crystal light valve nonlinearities in optical multilayer neural networks

Applied Optics

Volumn 35, Issue 26, 1996, Pages 5301-5307

  Moerland, P D ^a   Fiesler, E ^a   Saxena, I ^a  

^a IDIAP RESEARCH INSTITUTE   (Switzerland)

Author keywords

Activation function; Artificial neural network; Curve fit; Gain; Hardware implementation; Liquid crystal light valve (LCLV); Optical multilayer neural network

Indexed keywords

EID: 1542440438     PISSN: 1559128X     EISSN: 21553165     Source Type: Journal    
DOI: 10.1364/AO.35.005301     Document Type: Article

References (21)

1. F. Yu, T. Lu, X. Yang, and D. Gregory, “Optical neural network with pocket-sized liquid-crystal televisions, ” Opt. Lett. 15, 863-865 (1990).
2. J.-S. Jang, S.-G. Shin, S.-W. Yuk, S.-Y. Shin, and S.-Y. Lee, “Dynamic optical interconnections using holographic lenslet arrays for adaptive neural networks, ” Opt. Eng. 32, 80-87 (1993).
3. I. Shariv and A. A. Friesem, “All-optical neural network with inhibitory neurons, ” Opt. Lett. 13, 485-487 (1989).
4. D. Psaltis and Y. Qiao, “Adaptive multilayer optical networks, ” in Progress in Optics, E. Wolf, ed. (Elsevier, Amsterdam, The Netherlands, 1990), Vol. 31, Chap. 4, pp. 227-261
5. D. Psaltis and Y. Qiao, “Optical neural networks, ” Opt. Photon. News 1 (12), 17-21 (1990).
6. W. Xue, “Characterization of liquid crystal light valves for neural network applications, ” Ph.D. dissertation (Institute of Microtechnology, University of Neuchatel, Neuchatel, Switzerland, 1994).
7. M. G. Robinson and K. M. Johnson, “Noise analysis of polarization-based optoelectronic connectionist machines, ” Appl. Opt. 31, 263-272 (1992).
8. W. P. Bleha, L. T. Lipton, E. Wiener-Avnear, J. Grinberg, P. G. Reif, D. Casasent, H. B. Brown, and B. V. Markevitch, “Application of the liquid crystal light valve to real-time optical data processing, ” Opt. Eng. 17, 371-384 (1978).
9. I. Saxena and E. Fiesler, “Adaptive multilayer optical neural network with optical thresholding, ” (in specialissue on Optics in Switzerland, P. Rastogi, ed.) Opt. Eng. 34, 2435-2440 (1995).
10. E. Fiesler, “Neural network classification and formalization, ” in Computer Standards & Interfaces, specialissue on neural network standards, J. Fulcher, ed., (Elsevier, Amsterdam, The Netherlands, 1994), Vol. 16, pp. 231-239.
11. N. Collings and W. Xue, “Liquid-crystal light valves as thresholding elements in neural networks: basic device requirements, ” Appl. Opt. 33, 2829-2833 (1994).
12. Light valve obtained from Micro-Optics Technologies, 8608 University Green #5, Middleton, Wisc. 53562, U.S.A.
13. D. Rumelhart, G. Hinton, and R. Williams, “Learning internal representations by error propagation, ” in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1 of Massachusetts Institute of Technology Foundations Series, (MIT Press, Cambridge, Mass., 1986), pp. 318-362.
14. R. P. Gorman and T. J. Sejnowski, “Analysis of hidden units in a layered network trained to classify sonar targets, ” Neural Networks 1, 75-89 (1988).
15. Data made available in 1994 by librarians P. M. Murphy and D. W. Aha from the UCI Repository of Machine Learning Databases, a machine-readable data repository accessible by means of the anonymous ftp, Internet: ftp://ftp.ics.uci.edu/pub/machine-learning-databases.
16. G. Thimm and E. Fiesler, “Weight initialization in higher order and multi-layer perceptrons, ” IEEE Trans. Neural Net. (to be published)
17. G. Thimm and E. Fiesler, “Weight initialization in higher order and multi-layer perceptrons, ” in Proceedings of the’94 SIPAR-Workshop on Parallel and Distributed Computing, M. Aguilar, ed. (Institute of Informatics, University of Fribourg, Fribourg, Switzerland, 1994), pp. 8790.
18. J. M. C. Oosse, H. C. A. M. Withagen, and J. A. Hegt, “Analog VLSI implementation of a feed-forward neural network, ” paper presented at the First International Conference on Electronics, Circuits, and Systems (ICECS’94), 19-22 December 1994, Cairo, Egypt.
19. G. Thimm, P. Moerland, and E. Fiesler, “The interchangeability of learning rate and gain in backpropagation neural networks, ” Neural Computation 8, 451-460 (1996).
20. S. E. Fahlman, “An empirical study of learning speed in backpropagation networks, ” Tech. rep. CMU-CS-88-162 (School of Computer Science, Carnegie-Mellon University, Pittsburgh, Penna., 1988).
21. D. B. Mundie and L. W. Massengill, “Threshold non-linearity effects on weight-decay tolerance in analog neural networks, ” in Proceedings of the International Joint Conference on Neural Networks (IJCNN’92), (The Institute of Electrical and Electronics Engineers, Piscataway, N.J., 1992), Vol. 2, pp. 583-587.