Abstract
Artificial neural networks are parallel processing systems which have applications in speech and pattern recognition (Rumelhart and McCelland, 1986; Prager et al., 1986; Lippmann, 1987; Szu, 1986; Geman and Geman, 1984; Luttrell, 1985; Widrow et al. 1988), function optimization (Geman and Geman, 1984; Barhen et al., 1987; Hinton et al., 1984; Kirkpatrick et al., 1983; Hopfield and Tank, 1986), robotics (Barhen et al., 1987), and control (Psaltis et al., 1988a). They consist of a set of identical, nonlinear processing elements, generically known as neurons, which are linked together to form a highly interconnected network. Information is represented by the pattern of activity of the neurons and data are stored by distributing them throughout the network’s connections. This is done by weighting the links with positive and negative values to indicate the effect that one neuron has on another. This makes the system fault tolerant since each neuron is connected to many others and each weight represents the ‘average’ stimulus over the data set, so the loss of a few connections does not drastically affect the operation of the network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Athale, R. A. and Lee, J. N. (1984) Optical processing using outer-product concepts, Proc. IEEE, 72, 931–41.
Athale, R. A., Szu, H. H. and Friedlander, C. B. (1986) Optical implementation of associative memory with controlled nonlinearity in the correlation domain, Opt. Lett., 11, 482–4.
Barhen, J., Toomarian, N. and Protopopescu, V. (1987) Optimisation of the computational load of a hypercube supercomputer onboard a mobile robot, Appl. Opt., 26, 5007–14.
Bostel, A. J., Stace, C., Swinburn, G. and Hall, T. J. (1989) Optical computing based on neural systems. In Proc. Int. Symp. on Optics in Computing, SFO. Toulouse, October 17–18, 1989, pp. 187–94.
Bounds, D. G. (1987) A statistical mechanical study of Boltzmann machines, J. Phys. A, 20, 2133–45.
Bradley, E., Yu, P. K. L. and Johnston, A. R. (1989) System issues relating to laser diode requirements for VLSI holographic optical interconnections, Opt Eng., 28, 201–11.
Collins, D. R., Sampseil, J. B., Hornbeck, L. J. et al. (1989) Deformable mirror device spatial light modulators and their applicability to optical neural networks, Appl. Opt., 28, 4900–7.
Collins, S. A., Jr. (1988) Optical computing with spatial light modulators. In Optical Computing, Proc. 34th Scottish Universities Summer School in Physics, Heriot-Watt University, Edinburgh (eds B. S. Wherrett and F. A. P. Tooley), Scottish Universities Summer School in Physics, pp. 23–54.
Collings, N., Crossland, W. A., Ayliffe, P. J. et al. (1989) Evolutionary development of advanced liquid crystal spatial light modulators, Appl. Opt., 28, 4740–7.
Cronin-Golomb, M. and Yariv, A. (1986) Phase-conjugate mirrors as thresholding elements for optical associative memories. In SPIE Proc. Int. Optical Computing Conf., pp. 301–3.
Derthick, M. (1984) Variations on the Boltzmann machine learning algorithm, Carnegie—Mellon Unive rsity Tech. Rep. CMU-CS-84-120.
Farhat, N. H. (1987) Opto-electronic analogs of self-programming neural nets: architecture and methodologies for implementing fast stochastic learning by simulated annealing, Appl. Opt., 26, 5093–103.
Farhat, N. H. (1989) Optoelectronic neural networks and learning machines, IEEE Circ. Dev. Mag., September, 32–41.
Farhat, N. H., Psaltis, D., Prata, A. and Paek, E. (1985) Optical implementation of the Hopfield model, Appl. Opt., 24, 1469–75.
Feldman, M. R. and Guest, C. C. (1987) Computer generated holographic optical elements for optical interconnection of very large scale integrated circuits, Appl. Opt., 26, 4377–84.
Fisher, A. D., Lippincott, W. L. and Lee, J. N. (1987) Optical implementations of associative networks with versatile adaptive learning capabilities, Appl. Opt., 26, 5039–54.
Geman, S. and Geman, D. (1984) Stochastic relaxation, Gibbs distributions, and Bayesian restoration of images, IEEE Trans. Pat. Anal. Mach. Intel., 6(6), 721–41.
Goodman, J. W., Dias, A. R., Woody, L. M. and Erickson, J. (1979) Application of optical communication technology to optical information processing, Proc. Soc. Photo-Opt. Instrum. Eng., 190, 485–96.
Guest, C. C. and Tekolste, R. (1987) Designs and devices for optical bidirectional associative memories, Appl Opt., 26, 5055–60.
Hall, T. J., Jaura, R., Connors, L. M. and Foote, P. D. (1985) The photorefractive effect—a review, Prog. Quantum Electron., 10, 77–146.
Hebb, D. O. (1949) The Organization of Behavior, Wiley, New York.
Hinton, G. F., Sejnowski, T. J. and Ackley, D. H. (1984) Boltzmann machines: constraint satisfaction networks that learn, Tech. Rep. CMU-CS-84-119, Department of Computer Science, Carnegie-Mellon University.
Hopfield, J. J. (1982) Neural networks and physical systems with emergent collective computational abilities, Proc. Natl Acad. Sci. USA, 19, 2554–8
Hopfield, J. J. (1984) Neurons with graded response have collective computational properties like those of two-state neurons, Proc. Natl Acad. Sci. USA, 81, 3088–92.
Hopfield, J. J. and Tank, D. W. (1986) Computing with neural circuits: a model, Science, 233, 625–33.
Huang, T. S. (1971) Digital holography, Proc. IEEE, 59, 1335–46.
Jang, J., Shin, S. and Lee, S. (1988a) Optical implementation of quadratic associative memory with outer-product storage, Opt. Lett., 13, 693–5.
Jang, J., Jung, S., Lee, S. and Shin, S. (1988b) Optical implementation of the Hopfield model for two-dimensional associative memory, Opt. Lett., 13, pp. 248–50.
Johnson, K. M. and Moddel, G. (1990) Motivations for using ferroelectric liquid crystal spatial light modulators in neurocomputing, Appl. Opt., 28, 4888–99.
Kagan, D. and Friedman, H. (1989) Back propagating neurons from bichromic interaction with a three level system, Appl Opt., 28, 1697–1700.
Kirkpatrick, S., Gelatt, C. D. and Vecchi, M. P. (1983) Optimisation by simulated annealing, Science, 220, 671–80.
Kohonen, T. (1984) Self Organization and Associative Memory, Springer, New York.
Kosko, B. (1988) Bidirectional associative memories, IEEE. Trans. Sys. Man. Cybern., 18, 49–60.
Lee, L. S., Stoll, H. M. and Tackitt, M. C. (1989) Continuous-time optical neural network associative momory, Opt. Lett., 14, 162–4.
Lippmann, R. P. (1987) An introduction to computing with neural nets, IEEE ASSP Mag., April, 4–22.
Lu, T., Choi, K, Wu, S., Xu, X. and Yu, F. T. S. (1989) Optical disk based neural network, Appl Opt., 28, 4722–4.
Luttrell, S. P. (1985) The implications of Boltzmann-type machines for SAR data processing: a preliminary survey, RSRE Memo. 3815.
Marks II, R. J., Atlas, L. E., Oh, S. and Cheung, K. F. (1988) Optical processor architectures for alternating-projection neural networks, Opt. Lett., 13, 533–5.
McKenzie, D. S. and Sagi, M. A. S. (1986) The random bond Ising model on the Bethe lattice, J. Phys. A, 19, 3883.
Miller, D. A. B. (1988) Quantum well electro-absorptive devices: physics and applications. In Proc. 34th Scottish Universities Summer School in Physics, Heriot-Watt University, Edinburgh (eds B. S. Wherrett and F. A. P. Tooley), Scottish Universities Summer School in Physics, pp. 71–94.
Oita, M, Ohta, J., Tai, S. and Kyuma, K. (1990) Optical implementation of large-scale neural networks using a time-division multiplexing technique, Opt. Lett., 15, 227–9.
Pack, E. G., Wullert II, J. R., and Patel, J. S. (1989) Holographic implementation of a learning machine based on a multicategory perceptron algorithm, Opt. Lett., 14, 1303–5.
Pack, E. G., Wullert II, J. R., Jain, M. et al. (1990) Compact and ultrafast holographic memory using a surface emitting microlaser diode array, Opt. Lett., 15, 341–3.
Peltier, M. and Micheron, F. (1977) Volume hologram recording and charge transfer process in Bi12SiO20 and Bi12Ge20 (BSO and BGO), J. Appl. Phys., 48, 3683–90.
Powell, M., Powles, C. and Bagshaw, J. (1988) The effect of read/write isolation on the resolution of the Marconi spatial light modulator, Proc. Soc. Photo-Opt. Instrum. Eng., 936, 68–75.
Prager, R. W., Harrison, T. D. and Fallside, F. (1986) Boltzmann machine for speech recognition, Comput. Speech Lang. 1, 3–27.
Psaltis, D. and Farhat, N. H. (1985) Optical information processing based on an associative memory model of neural nets with thresholding and feedback, Opt. Lett., 10, 98–100.
Psaltis, D. and Hong, J. (1987) Shift-invariant optical associative memories, Opt. Eng., 26, 10.
Psaltis, D., Yu, Y., Gu, G. and Lee, H. (1987) Optical neural nets implemented with volume holograms. In Proc. Optical Computing Meet., Lake Tahoe, OSA CA, March 18–20, pp. 129–32.
Psaltis, D., Sideris, A. and Yamamura, A. A. (1988a) A multilayered neural network controller, IEEE Control Syst. Mag., April, 17–21.
Psaltis, D., Brady, D. and Wagner, K. (1988b) Adaptive optical networks using photorefractive crystals, Appl. Opt., 27, 1752–9.
Psaltis, D., Park, C. H. and Hong, J. (1988c) Higher order associative memories and their optical implementations, Neural Networks, 1, 149–63.
Psaltis, D., Brady, D., Gu, X. G. and Lin, S. (1990a) Holography in artificial neural networks, Nature (London), 343, 325–30.
Psaltis, D., Neifield, M. A., Yamamura, A. and Kobayashi, S. (1990b) Optical memory disks in optical information processing, Appl. Opt., 29, 2038–57.
Rumelhart, D. E. and McCelland, J. L. (eds) (1986) Parallel Distributed Processing, MIT, Cambridge, MA.
Rumelhart, D. E., Hinton, G. E. and Williams, R. J. (1986) Learning representations by back propagating errors, Nature (London), 323, 533–5.
Shamir, J., Caulfield, H. J. and Johnson, R. B. (1989) Massive holographic interconnection networks and their limitations, Appl. Opt., 28, 311–24.
Shariv, I. and Friesem, A. A. (1989) All-optical neural network with inhibitory neurons, Opt. Lett., 14, 485–7.
Smith, S. D. (1988) Optical circuits. In Proc. 34th Scottish Universities Summer School in Physics, Herriot-Watt University, Edinburgh (eds B. S. Wherrett and F. A. P. Tooley), Scottish Universities Summer School in Physics, pp. 95–132.
Soffer, B. H., Dunning, G. J., Owechko, Y. and Marom, E. (1986) Associative holographic memory with feedback using phase-conjugate mirrors, Opt. Lett., 11, 118–20.
Song, Q. W. and Yu, F. T. S. (1989) Holographic associative memory system using a thresholding microchannel spatial light modulator, Opt. Eng., 28, 533–6.
Staebler, D. L. and Amodei, J. J. (1972) Coupled-wave analysis of holographic storage in LiNbO3, J. Appl. Phys., 43, 1042–9.
Szu, H. (1986) Three layers of vector outer product neutral networks for optical pattern recognition, Proc. Soc. Photo-Opt. Instrum. Eng., 634, 312–30.
Tekolste, R. D. and Guest, C. C. (1987) Optical competitive neural network with Optical Feedback. In Proc. of IEEE 1st Int. Conf on Neural Networks, San Diego, CA, June 21–24, pp. III625–III629.
Ticknor, A. J. and Barrett, H. H. (1987) Optical implementations in Boltzmann machines, Opt. Eng., 26, 16–21.
Von Lehman, A., Pack, E. G, Carrion, L. C. et al. (1990) Optoelectronic chip implementation of a quadratic associative memory, Opt. Lett., 15, 279–81.
Wagner, K. and Psaltis, D. (1987) Multilayer optical learning networks, Appl. Opt., 26, 5061–76.
White, H. J. and Wright, W. A. (1988) Holographic implementation of a Hopfield model with discrete weightings, Appl. Opt., 27, 331–8.
White, H. J., Aldridge, N. B. and Lindsay, I. (1988) Digital and analogue holographic associative memories, Opt. Eng., 27, 30–7.
Widrow, B., Winter, R. G and Baxter, R. A. (1988) Layered neural nets for pattern recognition, IEEE Trahs. Acoust. Speech. Sig. Process., 36, 1109–18.
Williams, D., Latham, S. G, Powles, C. M. J. et al. (1988) An amorphous silicon/chiral smectic spatial light modulator, J. Phys. D, 21, 5156–9.
Yariv, A. and Kwong, S. (1986) Associative memories based on message bearing optical modes in phase conjugate resonators, Opt. Lett., 11, 186–8.
Yeh, P., Chang, T. Y. and Beckwith, P. H. (1988) Real-time optical image subtraction using dynamic holographic interference in photorefractive media, Opt. Lett., 13, 580–8.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1993 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Bostel, A.J., Powell, A.K., Hall, T.J. (1993). Architectures for Optical Neural Networks. In: Eason, R.W., Miller, A. (eds) Nonlinear Optics in Signal Processing. Engineering Aspects of Lasers Series, vol 49. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-1560-5_7
Download citation
DOI: https://doi.org/10.1007/978-94-011-1560-5_7
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-4681-7
Online ISBN: 978-94-011-1560-5
eBook Packages: Springer Book Archive