Neural processor element

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 27, G06G 716

Patent

active

056153058

ABSTRACT:
A neural processor element for use in a neural network includes a synaptic base weighting circuit which responds to an excitory input in the form of a stream of pulses of a first polarity which represents a sum of synaptic weights and an inhibitory input in the form of a stream of pulses of a second polarity which represents a sum of synaptic weights. The synaptic weight of the neural processor element is generated by summing the excitory and inhibitory pulse streams to produce a signal of varying level magnitude. This signal is subjected to a thresholding function which generates a pulse having a width corresponding to the sum of excitory and inhibitory pulse streams, this pulse width representing the synaptic weight for the neural processor element.

REFERENCES:
patent: 3103648 (1963-09-01), Hartmanis
patent: 3250918 (1966-03-01), McGrogan, Jr.
patent: 3308441 (1967-03-01), Dusheck, Jr.
patent: 3348214 (1967-10-01), Barbetta
patent: 3457552 (1969-07-01), Asendorf
patent: 3548385 (1970-12-01), Tunis
patent: 3701974 (1972-10-01), Rusell
patent: 3950733 (1976-04-01), Cooper et al.
patent: 4094307 (1978-06-01), Young, Jr.
patent: 4193115 (1980-03-01), Albus
patent: 4254474 (1981-03-01), Cooper et al.
patent: 4419544 (1983-12-01), Adelman
patent: 4479241 (1984-10-01), Buckley
patent: 4637402 (1987-01-01), Adelman
patent: 4660166 (1987-04-01), Hopfield
patent: 4709327 (1987-11-01), Hillis et al.
patent: 4731747 (1988-03-01), Denker
patent: 4748439 (1988-05-01), Robinson
patent: 4750153 (1988-06-01), Owechko
patent: 4752906 (1988-06-01), Kleinfeld
patent: 4762397 (1988-08-01), Pepper
patent: 4827453 (1989-05-01), Sawada et al.
patent: 4829199 (1989-05-01), Prater
patent: 4875183 (1989-10-01), Graf et al.
patent: 4893255 (1990-01-01), Tomlinson, Jr.
patent: 4903226 (1990-02-01), Tsividis
patent: 4906865 (1990-03-01), Holler
patent: 4950917 (1990-08-01), Holler et al.
patent: 4951239 (1990-08-01), Andes et al.
patent: 4956564 (1990-09-01), Holler et al.
patent: 4961002 (1990-10-01), Tam et al.
patent: 4965767 (1990-10-01), Kinoshita et al.
patent: 4985644 (1991-01-01), Okihara et al.
patent: 4988891 (1991-01-01), Mashiko
patent: 5010512 (1991-04-01), Hartstein et al.
patent: 5021693 (1991-06-01), Shima
patent: 5095267 (1992-03-01), Merrill et al.
patent: 5126692 (1992-06-01), Shearer et al.
patent: 5196741 (1993-03-01), Rustici
Brownlow et al, "Pulse-Firing Neural Chips for Hundreds of Neurons", Advance in Neural Information Processing System 2, Nov. 1989, Morgan Kaufmann Publishers.
"Neural Computing, Theory and Practice" Philip D. Wasserman, Apr. 1989.
"VLSI Technologies for Artificial Neural Networks", IEEE 1989 by Karl Goser.
"An Analog CMOS Backward. Error-Propagation LSI" B. Furman and A.A. Abidi, Presented at First Annual InnS Sympocium, Sep. 1988.
Murray et al, "Pulse-Firing Neural Chips for Hundreds of Neurons", 1989 IEEE Conf. on Neural Inf. Processing System, Morgan Kaufmann.
Murray et al, "Programmable Analog Pulse-Firing Neural Networks", 1988 IEEE Conf. on Neural Inf. Processing System, Morgan Kaufmann.
Murray et al, "Asynchronous VLSI Neural Networks using Pulse - Stream Arithmetic", IEEE Journal of Solid State Circuits, Jun. 1988.
Fink "Electronics Engineers Handbook" McGraw Hill, 1975.

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 processor element 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 processor element, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural processor element will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2211130

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