Neural net using capacitive structures connecting input lines an

Details Neural net using capacitive structures connecting input lines an Neural net using capacitive structures connecting input lines an

1991-12-18

1993-02-16

Baker, Stephen M.

Boots, shoes, and leggings

307201, 395 24, 395 27, G06G 712, G06G 706

Patent

active

051876809

ABSTRACT:
Neural nets using capacitive structures are adapted for construction in complementary metal-oxide-semiconductor integrated-circuit technology. In each neural net layer synapse input signals are applied to the inverting and non-inverting input terminals of each of a plurality of differential-input non-linear amplifiers by a respective pair of capacitors, which non-linear amplifiers generate respective axon responses. In certain of these neural nets, arrangements are described that make the capacitive structures bilaterally responsive, so that back-propagation calculations can be performed to alter the relative values of capacitors in each pair thereof, which is done during training of certain of the neural nets described.

REFERENCES:
patent: 3890618 (1975-06-01), Speiser
patent: 3890635 (1975-06-01), Engeler
patent: 4156284 (1979-05-01), Engeler
patent: 4161785 (1979-07-01), Gasparek
patent: 4267580 (1981-05-01), Bond et al.
patent: 4288858 (1981-09-01), Merola et al.
patent: 4873455 (1989-10-01), de Chambost et al.
patent: 4903226 (1990-02-01), Tsividis
patent: 4950917 (1990-08-01), Holler et al.
patent: 4951239 (1990-08-01), Andes et al.
Sequin, C., et al., "Self-Contained Charge-Coupled Split-Electrode Filters Using a Novel Sensing Technique", IEEE J. Solid-State Circuits, vol. SC-12, No. 6, Dec. 1977, pp. 626-632.
"EG&G Reticon R5403 Analog-Analog Correlator/Convolver", copyright 1979, 5 pages of R5403 description and typical applications.
Lau, G., "Neural Networks, I: Theory and Modelling", Proc. IEEE, vol. 78, No. 9, Sep. 1990, pp. 1411-1414.
Widrow B. et al., "30 Years of Adaptive Neural Networks: Perceptron, Madaline, and Backpropagation", Proc. IEEE, vol. 78, No. 9, Sep. 1990, pp. 1415-1441.
Moore, S., "Eliminate the guesswork in analog-switch error analysis", EDN, Nov. 26, 1987, pp. 219-225.
Raffel, J., "Electronic Implementation of Neuromorphic Systems", IEEE Custom Integrated Circuits Conf., May 1988, pp. 10.1.1-10.1.7.
Wasserman, P. et al., "Neural Networks, Part 2: What are they and why is everybody so interested in them now?", IEEE Expert, Spring 1988, pp. 10-15.
Bibyk, S. et al., "Issues in Analog VLSI and MOS Techniques for Neural Computing", Analog VLSI Implementation of Neural Systems, Mead, C., et al., eds., copyright 1989 by Kluwer Academic Publishers, pp. 103-133.
Herrman, E. et al., "Programmable CCD Correlator", IEEE Trans. on Electron Devices, vol. ED-26, No. 2, Feb. 1979, pp. 117-122.
Sage, J. et al., "CCD Analog-Analog Correlator with Four-FET Bridge Multipliers", Proc. 11th. Conf. on Solid-Devices, Tokyo, 1979, Japan J. of Appl. Phys., vol. 19 (1980), Sppl. 19-1, pp. 265-268.
Mavor, J. et al., "A Monolithic CCD Programmable Transversal Filter for Analogue Signal Processing", The Radio and Electronic Engineer, vol. 50, No. 5, pp. 213-225, May 1980.
Kub, F. et al., "Programmable Analog Synapses for Microelectronic Neural Networks Using a Hybrid Digital-Analog Approach", Submitted to IEEE Int'l. Conf. on Neural Networks, Jul. 24-27, San Diego.
"An Introduction to Computing With Neural Nets", R. P. Lippmann, IEEE ASSP Magazine, Apr. 1987, pp. 4-22.
"Switched-Capacitor Neural Networks", Y. P. Tsividis & D. Anastassion, Electronics Letters, Aug. 27, 1987, vol. 23, No. 18, pp. 958-959.
"Analog MOS Integrated Circuits for Signal Processing", R. Gregorian & G. C. Temes, pp. 255-237, John Wiley & Sons, NYC, Chichester, Brisbane, Toronto, Singapore 1986.

Affiliated with

Also associated with

Rating

Neural net using capacitive structures connecting input lines an 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 net using capacitive structures connecting input lines an, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural net using capacitive structures connecting input lines an will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2152950