1995-06-07
1997-10-07
Davis, George B.
395 22, G06F 1518
Patent
active
056757131
ABSTRACT:
An artificial neuron for use in a neural processing network comprises a plurality of input signal lines, an arrangement for computing a nonlinear function of the sum of the inputs multiplied by associated weights, and a saturating delta-sigma modulator which oversamples the computed value and produces an encoded neuron output signal. Conversion of signals for use by these neurons preferably is performed by delta-sigma modulators at the inputs to the neurons, which may be incorporated directly into sensors. Processing of the output signals from the neuron includes low-pass filtering and decimation. The present invention may be used in many diverse areas. For example, arrays of sensors with delta signal modulators may be coupled with a network of the neurons to form an intelligent vision system. Linear signal processing, both conventional and adaptive, can be done by a simple neuronal system that operates linearly.
REFERENCES:
patent: 3293609 (1966-12-01), Martin
patent: 3435422 (1969-03-01), Gerhardt et al.
patent: 3601811 (1971-08-01), Yoshino
patent: 4891782 (1990-01-01), Johnson
patent: 4994982 (1991-02-01), Duranton et al.
patent: 5003490 (1991-03-01), Castelaz et al.
patent: 5091864 (1992-02-01), Baji et al.
patent: 5093900 (1992-03-01), Graf
patent: 5097141 (1992-03-01), Leivian et al.
patent: 5142666 (1992-08-01), Yoshizawa et al.
patent: 5151970 (1992-09-01), Engeler
patent: 5165010 (1992-11-01), Musada et al.
patent: 5170071 (1992-12-01), Shreve
patent: 5175798 (1992-12-01), Taylor et al.
patent: 5195171 (1993-03-01), Takatori et al.
patent: 5211622 (1993-05-01), Liboff et al.
patent: 5262968 (1993-11-01), Coffield
patent: 5359700 (1994-10-01), Seligson
patent: 5379252 (1995-01-01), Yamamoto
patent: 5381804 (1995-01-01), Shambroom
Widrow, Bernard, et al., "30 Years of Adaptive Neural Networks: Perceptron, Madaline, and Backpropagation", Proceedings of the IEEE, vol. 78, No. 9, Sep. 1990.
Park, Ph.D., Sangil, "Principles of Sigma-Delta Modulation for Analog-to-Digital Converters," Apr. 8, 1990, Motorola, Inc.
Candy, James C., et al., "Oversampling Delta-Sigma Data Converters Theory, Design, and Simulation," The Institute of Electrical and Electronics Engineers, Inc., New York.
Watanabe, Takao, et al, "A Single 1.5-V Digital Chip for a 10.sup.6 Synapse Neural Network," IEEE Transactions on Neural Networks, vol. 4, No. 3, May 1993.
Widrow, Bernard, et al., "The Adaptive Linear Combiner," Adaptive Signal Processing, 1985, Chapter 2, pp. 15-26.
Rabiner, Lawrence R., et al., "Theory and Application of Digital Signal Processing", Prentice-Hall, Inc., Englewood Cliffs, New Jersey, pp. 326-329.
Oppenheim, Alan V., et al., "Digital Signal Processing," Prentice-Hall, Inc., Englewood Cliffs, New Jersey, pp. 413-432.
Gorse, D., et al., "On the Equivalence and Properties of Noisy Neural and Probabilistic Ram Nets," Physics Letters A, vol. 131, No. 6, pp. 326-332, Aug. 29, 1988.
Shandle, Jack, "Neural Networks are Ready for Prime Time," Electronic Design, Feb. 18, 1993, pp. 51-58.
Lippmann, Richard P., "An Introduction to Computing with Neural Nets," IEEE ASSP Magazine, Apr. 1987.
Duranton, et al., "A General Purpose Digital Architecture for Neural Network Simulations", 1st IEE Inter. Conf. on Artificial Neural Networks, 16-18 Oct. 1989.
Duranton, et al., "The LNeuro Chip: A Digital VLSI On-Chip Learning Mechanism", figure 1, Int'l Neural Network Conference, Jul. 9-13, 1990.
Davis George B.
Heim Michael F.
LandOfFree
Sensor for use in a 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 Sensor for use in a neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Sensor for use in a neural network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2364414