Neural network that incorporates direct optical imaging

Data processing: artificial intelligence – Neural network – Structure

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

G06F 1518

Patent

active

058421912

ABSTRACT:
A compact neural network architecture is trainable to sense and classify an optical image directly projected onto it. The system is based upon the combination of a two-dimensional amorphous silicon photoconductor array and a liquid-crystal spatial light modulator. Appropriate filtering of the incident optical image upon capture is incorporated into the net work training rules, through a modification of the standard backpropagation training algorithm. Training of the network on two image classification problems is described: the recognition of handprinted digits, and facial recognition. The network, once trained is capable of standalone operation, sensing an incident image and outputting a final classification signal in real time.

REFERENCES:
patent: 4762397 (1988-08-01), Pepper
patent: 4892370 (1990-01-01), Lee
patent: 4963725 (1990-10-01), Hong et al.
patent: 5080464 (1992-01-01), Toyoda
patent: 5129040 (1992-07-01), Hanazato et al.
patent: 5220642 (1993-06-01), Takahashi et al.
patent: 5255362 (1993-10-01), Brandstetter et al.
patent: 5428711 (1995-06-01), Akiyama et al.
patent: 5515189 (1996-05-01), Kuratomi et al.
Applied Optics, vol. 32, No. 26, Sep. 10, 1993, "Optically Programmed Neural Network Capable of Stand-Alone Operation", pp. 5141-5152, by R.G. Stearns.
Optoelectronics Devices and Technologies, vol. 8, No. 1, Mar. 1, 1993, "Optical Neuro-Devices", pp. 35-52, by Kazuo Kyuma, et al.
Stearns, Richard G., "Trainable Optically Programmed Neural Network," Applied Optics, vol. 31, No. 29, pp. 6230-6239, Oct. 10, 1992.
Stearns, Richard G. et al., "Two-Dimensional Amorphous-Silicon Photoconductor Array for Optical Imaging," Applied Optics, vol. 31, No. 32, pp. 6874-6881, Nov. 10, 1992.
Rietman, Edward A. et al., "Signal Prediction by an Optically Controlled Neural Network," Applied Optics, vol. 30, No. 8, pp. 950-957, Mar. 10, 1991.
Rietman, Edward A. et al., "Amorphous Silicon Photoconductive Arrays for Artificial Neural Networks," Applied Optics, vol. 28, No. 15, pp. 3474-3478, Aug. 15, 1988.
Stearns, Richard G., "A Neural Network That Incorporates Direct Optical Imaging," pp. 1-27, submitted for publication, but not published.
Stearns, Richard G., "An Optically-Programmed Neural Network Capable of Standalone," Applied Optics, pp. 1-42, Apr. 1993.
Rumelhart, D.E. et al., "Learning Internal Representations by Error Propagation," Parallel Distributed Processing, D.F., vol. 1, Chap. 8, pp. 319-339, 1986.
Lippmann, Richard P., "An Introduction to Computing With Neural Nets," IEEE ASSP Magazine, pp. 4-22, Apr. 1987.
Widrow, Bernard et al., "Neural Nets for Adaptive Filtering and Adaptive Pattern Recognition," Computer, pp. 25-39, Mar. 1988.
Nguyen, Derrick H. et al., "Neural Networks for Self-Learning Control Systems," Control Systems Magazine, pp. 18-23, Apr. 1990.
Widrow, Bernard et al., "30 Years of Adaptive Neural Networks: Perceptron, Madaline, and Backpropagation," Proceedings of the IEEE, vol. 78, No. 9, pp. 1415-1442, Sep. 1990.
Stearns, Richard G., "A Neural Network That Incorporates Direct Optical Imaging," pp. 1-27, Jan. 24, 1994.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Neural network that incorporates direct optical imaging does not yet have a rating. At this time, there are no reviews or comments for this patent.

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

Rate now

     

Profile ID: LFUS-PAI-O-1715027

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.