IV Adaptive Multilayer Optical Networks

Publisher Summary This chapter discusses the adaptive multilayer optical networks. The chapter describes an experimental two-layer optical neural network recently built at California Institute of Technology. The system is trained for handwritten character recognition, and the experimental results are provided in the chapter. The implementation of fully adaptive learning algorithms in such a network is discussed. The chapter describes a local learning algorithm for fully adaptive two-layer networks. The problem of hologram decay is discussed and a solution using periodic copying is described. The chapter presents a system that provides phase-locked sustainment of photorefractive holograms. The hologram copying method is a promising solution for the device dynamic range problems. As for the training of multilayer networks, large networks require very large training sets. Understanding such algorithmic issues about the training of large optical networks is the major challenge before these systems can have a practical impact.

[1]  J N Lee,et al.  Optical implementations of associative networks with versatile adaptive learning capabilities. , 1987, Applied optics.

[2]  D. Psaltis,et al.  Volume holographic interconnections with maximal capacity and minimal cross talk , 1989 .

[3]  Demetri Psaltis.  Optical Neural Networks. , 1987 .

[4]  Demetri Psaltis,et al.  Optical Neural Computers , 1987, Topical Meeting on Optical Computing.

[5]  Amnon Yariv,et al.  Optical limiters using photorefractive nonlinearities , 1985 .

[6]  N H Farhat,et al.  Optoelectronic analogs of self-programming neural nets: architecture and methodologies for implementing fast stochastic learning by simulated annealing. , 1987, Applied optics.

[7]  B H Soffer,et al.  Associative holographic memory with feedback using phase-conjugate mirrors. , 1986, Optics letters.

[8]  K Wagner,et al.  Multilayer optical learning networks. , 1987, Applied optics.

[9]  J. J. Amodei,et al.  HOLOGRAPHIC PATTERN FIXING IN ELECTRO‐OPTIC CRYSTALS , 1971 .

[10]  J. J. Amodei,et al.  Coupled‐Wave Analysis of Holographic Storage in LiNbO3 , 1972 .

[11]  Jack Feinberg,et al.  Asymmetric self-defocusing of an optical beam from the photorefractive effect , 1982 .

[12]  H Toyoda,et al.  Experimental studies on learning capabilities of optical associative memory. , 1990, Applied optics.

[13]  A. Yariv,et al.  Associative memories based on message-bearing optical modes in phase-conjugate resonators. , 1986, Optics letters.

[14]  F. Mok,et al.  Storage of 500 high-resolution holograms in a LiNbO(3) crystal. , 1991, Optics letters.

[15]  D. Psaltis,et al.  Phase-locked sustainment of photorefractive holograms using phase conjugation , 1991 .

[16]  E G Paek,et al.  Holographic implementation of a learning machine based on a multicategory perceptron algorithm. , 1989, Optics letters.

[17]  C C Guest,et al.  Designs and devices for optical bidirectional associative memories. , 1987, Applied optics.

[18]  Demetri Psaltis,et al.  Optical Associative Memory Using Fourier Transform Holograms , 1987 .

[19]  Demetri Psaltis,et al.  Higher order associative memories and their optical implementations , 1988, Neural Networks.

[20]  Philip A. Chou,et al.  The capacity of the Kanerva associative memory , 1989, IEEE Trans. Inf. Theory.

[21]  A. B. Vander Lugt,et al.  Signal detection by complex spatial filtering , 1964, IEEE Trans. Inf. Theory.

[22]  R A Athale,et al.  Optical implementation of associative memory with controlled nonlinearity in the correlation domain. , 1986, Optics letters.

[23]  D. Psaltis,et al.  Periodically refreshed multiply exposed photorefractive holograms. , 1990, Optics letters.

[24]  S Campbell,et al.  Optical pattern classifier with Perceptron learning. , 1990, Applied optics.

[25]  Lawrence D. Jackel,et al.  Backpropagation Applied to Handwritten Zip Code Recognition , 1989, Neural Computation.

[26]  M. Soskin,et al.  Holographic storage in electrooptic crystals. i. steady state , 1978 .

[27]  S Y Lee,et al.  Programmable quadratic associative memory using holographic lenslet arrays. , 1989, Optics letters.

[28]  D. Psaltis,et al.  Holography in artificial neural networks , 1990, Nature.

[29]  A Von Lehmen,et al.  Holographic associative memory for word-break recognition. , 1989, Optics letters.

[30]  H. B. Brown,et al.  Application Of The Liquid Crystal Light Valve To Real-Time Optical Data Processing , 1978 .

[31]  M. Tackitt,et al.  Continuous-time optical neural network associative memory. , 1989, Optics letters.

[32]  Mark A. Handschy,et al.  High-speed binary optically addressed spatial light modulator , 1989 .

[33]  D. Z. Anderson,et al.  Coherent optical eigenstate memory. , 1986, Optics letters.

[34]  D. Brady,et al.  Adaptive optical networks using photorefractive crystals. , 1988, Applied optics.

[35]  D Psaltis,et al.  Optical information processing based on an associative-memory model of neural nets with thresholding and feedback. , 1985, Optics letters.

[36]  K M Johnson,et al.  Optical implementation of a second-order neural network. , 1991, Optics letters.

[37]  J Shamir,et al.  Design for a massive all-optical bidirectional associative memory: the big BAM. , 1988, Applied optics.

[38]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[39]  P. J. van Heerden,et al.  Theory of Optical Information Storage in Solids , 1963 .

[40]  K. Blotekjaer.  Limitations on holographic storage capacity of photochromic and photorefractive media. , 1979, Applied optics.

[41]  D Psaltis,et al.  Optical implementation of the Hopfield model. , 1985, Applied optics.