Method of increasing the accuracy of an analog neural network an

Details Method of increasing the accuracy of an analog neural network an Method of increasing the accuracy of an analog neural network an

1990-12-26

1992-09-08

Shaw, Dale M.

Boots, shoes, and leggings

364807, G06C 700

Patent

active

051466023

ABSTRACT:
A method for increasing the accuracy of an analog neural network which computers a sum-of-products between an input vector and a stored weight pattern is described. In one embodiment of the present invention, the method comprises initially training the network by programming the synapses with a certain weight pattern. The training may be carried out using any standard learning algorithm. Preferably, a back-propagation learning algorithm is employed.
Next, network is baked at an elevated temperature to effectuate a change in the weight pattern previously programmed during initial training. This change results from a charge redistribution which occurs within each of the synapses of the network. After baking, the network is then retrained to compensate for the change resulting from the charge redistribution. The baking and retraining steps may be successively repeated to increase the accuracy of the neural network to any desired level.

REFERENCES:
patent: 4719591 (1988-01-01), Hopfield et al.
patent: 4874963 (1989-10-01), Alspector
patent: 4943556 (1990-07-01), Szu
patent: 4977540 (1990-12-01), Goodwin et al.
patent: 5036479 (1991-07-01), Prednis et al.

Affiliated with

Also associated with

Rating

Method of increasing the accuracy of an analog neural network 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 Method of increasing the accuracy of an analog neural network an, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of increasing the accuracy of an analog neural network an will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-142027