Electrical transmission or interconnection systems – Nonlinear reactor systems – Parametrons
Patent
1992-03-12
1993-08-17
Hudspeth, David R.
Electrical transmission or interconnection systems
Nonlinear reactor systems
Parametrons
395 24, G06F 700
Patent
active
052372103
ABSTRACT:
A neural network providing correlation learning in a synapse cell coupled to a circuit for parallel implementation of weight adjustment in a broad class of learning algorithms. The circuit provides the learning portion of the synaptic operation and includes a pair of floating gate devices sharing a common floating gate member that stores the connection weight of the cell. Parallel weight adjustments are performed in a predetermined number of cycles utilizing a novel debiasing technique.
REFERENCES:
patent: 4904881 (1990-02-01), Castro
patent: 4906865 (1990-03-01), Holler
patent: 4950917 (1990-09-01), Holler et al.
patent: 4956564 (1990-09-01), Holler et al.
patent: 4961002 (1990-10-01), Tam et al.
patent: 5021693 (1991-06-01), Shima
patent: 5040134 (1991-08-01), Park
patent: 5053638 (1991-10-01), Furutani et al.
patent: 5101361 (1992-03-01), Eberhardt
patent: 5146542 (1992-09-01), Engeler
Mackie, et al., "Implementations of Neural Network Models in Silicon"; Oct., 1987.
Lippman, R., "An Introduction to Computing with Neural Nets"; IEEE ASSP, Apr. 1987.
Hopfield, et al., "Computing with Neural Circuits: A Model"; Science, Aug., 1986.
Graf, et al., "Analog Electronic Neural Network Circuits"; IEEE Circuits and Devices, Jul. 1989.
Hudspeth David R.
Intel Corporation
LandOfFree
Neural network accomodating parallel synaptic weight adjustments 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 accomodating parallel synaptic weight adjustments, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network accomodating parallel synaptic weight adjustments will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2246381