Optical neural network

Details Optical neural network Optical neural network

1989-07-05

1992-03-10

Smith, Jerry

Boots, shoes, and leggings

364822, 364807, G09C 1500, G06G 700, G06E 300

Patent

active

050954598

ABSTRACT:
An optical neural network which imitates a biological neural network, to provide an associative and/or pattern recognition function, is made of light emitting elements to represent an input neuron state vector, a correlation matrix which modulates light according to stored vector information, light receiving elements, an accumulator and a comparator to perform a threshold function. A stored vector closest to an input vector can be found from a large amount of information without increasing the system size by dividing the correlation matrix and the input neuron state vector with time division techniques, frequency modulation or phase modulation techniques. Positive and negative valves can also be provided with similar techniques.

REFERENCES:
patent: 4567569 (1986-01-01), Caulfield et al.
patent: 4633428 (1986-12-01), Byron
patent: 4704702 (1987-11-01), Groutzoulis
patent: 4862406 (1989-08-01), Fisher
Author-Nabil H. Farhat, Demetris Psaltis, Aluizio Prata and Eung Paek, "Optical Implementation of the Hopfield Model", 1985, vol. 24, p. 1469.
Author-Ju-Seog Jang et al., "Optical Implementation of the Hopfield Model for Two-Dimensional Associative Memory", Mar. 1988, vol. 13, No. 3.
Anthony M. Tai, "Low-Cost LCD Spatial Light Modulator with High Optical Quality", 5/1/86, Applied Optics No. 9, vol. 25.
"The Institute of Electronics, Information and Communication Engineers Technical Research Report", vol. 87, No. 385, Date: Feb. 23, 1988.
Author-J. J. Hopfield, "Neural Networks and Physical Systems with Emergent Collective Computational Abilities," 1982, vol. 79, pp. 2554-2558.
Author-Demetri Psaltis and Nabil Farhat, "Optical Information Processing Based on an Associative-Memory Model of Neural Nets and Feedback with Thresholding", vol. 10, 1985, No. 2.

Affiliated with

Also associated with

Rating

Optical neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Optical neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Optical neural network will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2289812