A continuous-time optical neural network

A description is given of the architecture and functioning of an all-optical, continuous-time recurrent neural network. The network is a ring resonator which contains a saturable, two-beam amplifier, two volume holograms, and a linear, two-beam amplifier. The saturable amplifier permits, through the use of a spatially patterned signal beam, the realization of an optical neuron array; the two volume holograms provide global network interconnectivity; and the linear amplifier supplies sufficient cavity gain to permit resonant, convergent operation of the network. Numerical solutions of the network equations of motion indicate that, for real-valued neural state vectors, the network functions in much the same way as either J.J. Hopfield's continuous-time model (1984) or a continuous-time version of D.Z. Anderson and M.C. Erie's BSB model (1987). For complex-valued neural state vectors, the network always converges to the dominant network attractor, thereby suggesting a paradigm for solving optimization problems in which entrapment by local minima is avoided.<<ETX>>

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

[2]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[3]  Y Owechko,et al.  Optoelectronic resonator neural networks. , 1987, Applied optics.

[4]  H. K. Liu,et al.  An optical inner-product array processor for associative retrieval , 1986, Photonics West - Lasers and Applications in Science and Engineering.

[5]  Dana Z. Anderson,et al.  Resonator Memories And Optical Novelty Filters , 1987 .

[6]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[7]  M S Cohen,et al.  Design of a new medium for volume holographic information processing. , 1985, Applied optics.

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

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

[10]  A Yariv,et al.  Theory of laser oscillation in resonators with photorefractive gain. , 1985, Optics letters.

[11]  Kazuo Kyuma,et al.  Demonstration of an all‐optical associative holographic memory , 1986 .

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

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

[14]  Y. Fainman,et al.  Optimal coherent image amplification by two-wave coupling in photorefractive BaTiO3 , 1986 .

[15]  Chris K. Karaguleff,et al.  The Interconnectability Of Neuro-Optic Processors , 1986, Optics & Photonics.

[16]  J. J. Hopfield,et al.  “Neural” computation of decisions in optimization problems , 1985, Biological Cybernetics.

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

[18]  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.

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