Patent
1994-08-29
1996-04-02
Downs, Robert W.
395 23, 395 27, G06F 1518
Patent
active
055048390
ABSTRACT:
A synaptic processor for use in a neural network produces a result signal in response to an input signal. The synaptic processor initializes an input expectation and receives an input signal. The synaptic processor determines a net modification to the the input expectation. The net modification to the input expectation has an increase term and a decrease term. The increase term is determined as a function of the input signal. The decrease term is independent of the magnitude of the input signal and is a function of a decay constant. The synaptic processor produces a result signal in response to the input expectation.
REFERENCES:
patent: 3097349 (1963-07-01), Putzrath et al.
patent: 3103648 (1963-09-01), Hartmanis
patent: 3165644 (1965-01-01), Clapper
patent: 3218475 (1965-11-01), Hiltz
patent: 3293609 (1966-12-01), Martin
patent: 3308441 (1967-03-01), Dusheck, Jr.
patent: 3310783 (1967-03-01), Putzrath
patent: 3310784 (1967-03-01), Hilinski
patent: 3351783 (1967-11-01), Harris et al.
patent: 3413735 (1968-12-01), Harris et al.
patent: 4518866 (1985-05-01), Clymer
patent: 4802103 (1989-01-01), Faggin et al.
patent: 4912649 (1990-03-01), Wood
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5093900 (1992-03-01), Graf
Caudill, "Neural Networks Primer--Part V", AI Expert, Nov. 1988, pp. 57-65.
Caudill, "Neural Networks Primer--Part VI", AI Expert, Feb., 1989, pp. 61-67.
Caudill, "Neural Networks Primer--Part VII", AI Expert, May 1989, pp. 51-58.
A Drive-Reinforcement Neural Network of Simple Instrumental Conditioning--J. S. Morgan et al--Pub. 1990.
A Neuronal Model of Classical Conditioning--A. Harry Klopf Pub. 1988.
Drive-Reinforcement Learning: A Self Supervised Model for Adaptive Control--James S. Morgan--Sub. to Mach. Learning (1990).
Pattern-Recognition by an Artificial Network Derived from Biologic Neuronal Systems--D. L. Alkon et al, Pub. 1990.
Article: The Role of Time of Natural Intelligence: Implications of Classical and Instrumental Conditioning for Neuronal and Neural Network Modeling; By: A. H. Klopf et al.; Published: 1990.
Caterpillar Inc.
Downs Robert W.
Mobus George E.
Yee James R.
LandOfFree
Processor and processing element 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 Processor and processing element for use in a neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Processor and processing element for use in a neural network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2022886