The use of fixed holograms for massively-interconnected, low-power neural networks

Publisher Summary Fixed, massively interconnected optical neural networks can be fast, inexpensive, adaptive, and powerful. Holograms can be used to connect each of N × N input signals to each of N × N output positions through N 4 independent, parallel, weighted interconnections. We explore the theory and practice of making optical neural networks using such holograms.

[1]  S Y Lee,et al.  Optical implementation of the Hopfield model for two-dimensional associative memory. , 1988, Optics letters.

[2]  J Shamir,et al.  Wave particle duality considerations in optical computing. , 1989, Applied optics.

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

[4]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

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

[6]  Stephen Grossberg,et al.  Nonlinear neural networks: Principles, mechanisms, and architectures , 1988, Neural Networks.

[7]  H. J. Caulfield,et al.  Optical neural networks , 1989 .

[8]  N H Farhat.  Architectures for optoelectronic analogs of self-organizing neural networks. , 1987, Optics letters.

[9]  S Grossberg,et al.  Masking fields: a massively parallel neural architecture for learning, recognizing, and predicting multiple groupings of patterned data. , 1987, Applied optics.

[10]  Charles F. Hester,et al.  Mapping Sequential Processing Algorithms Onto Parallel Distributed Processing Architectures , 1988, Photonics West - Lasers and Applications in Science and Engineering.

[11]  A A Sawchuk,et al.  Optical crossbar interconnections using variable grating mode devices. , 1987, Applied optics.

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

[13]  H J White,et al.  Holographic implementation of a Hopfield model with discrete weightings. , 1988, Applied optics.

[14]  Charles F. Hester,et al.  Solid optical correlators , 1990, Photonics West - Lasers and Applications in Science and Engineering.

[15]  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.

[16]  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.

[17]  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.

[18]  H. J. White,et al.  Digital and analogue holographic associative memories , 1988 .

[19]  J Shamir,et al.  Massive holographic interconnection networks and their limitations. , 1989, Applied optics.

[20]  Gilmore J. Dunning,et al.  Optoelectronic Neural Networks Based On Holographically Interconnected Image Processors , 1988, Photonics West - Lasers and Applications in Science and Engineering.

[21]  Joseph Shamir,et al.  Improved Architectures For Massive Holographic Interconnection Network , 1989, Other Conferences.

[22]  H J Caulfield.  Parallel N(4) weighted optical interconnections. , 1987, Applied optics.