Memory modification of artificial neural networks

Details Memory modification of artificial neural networks Memory modification of artificial neural networks

1989-09-18

1991-12-24

Fleming, Michael R.

Electrical pulse counters, pulse dividers, or shift registers: c

Counting or dividing in incremental steps

Beam type tube

377 2, 395 24, G06F 1546

Patent

active

050758683

ABSTRACT:
An artificial neural network, which has a plurality of neurons each receiving a plurality of inputs whose effect is determined by adjust able weights at synapses individually connecting the inputs to the neuron to provide a sum signal to a sigmoidal function generator determining the output of the neuron, undergoes memory modification by a steepest-descent method in which individual variations in the outputs of the neurons are successively generated by small perturbations imposed on the sum signals. As each variation is generated on the output of a neuron, an overall error of all the neuron outputs in relation to their desired values is measured and compared to this error prior to the perturbation. The difference in these errors, with adjustments which may be changed as the neuron outputs converge toward their desired values, is used to modify each weight of the neuron presently subjected to the perturbation.

REFERENCES:
patent: 4660166 (1987-04-01), Hopfield
patent: 4719591 (1988-01-01), Hopfield et al.
patent: 4755963 (1988-07-01), Denker et al.
Widrow, B. and Hoff, M. E.; "Adaptive Switching Circuits", Institute of Ro Engineers, Western Electric Show and Convention, Convention Record, Part 4, pp. 96-104 (1960).
Widrow, B., Winter, R. G., and Baxter, R. A.; "Learning Phenomena in Layered Networks", IEEE First International Conference on Neural Networks, (Sep. 1988).
Rumelhart, D. E., Hinton, G. E., and Williams, R. J.; "Learning Internal Representations by Error Propagation", Parallel Distributed Processing, Chap. 8, pp. 318-328, The MIT Press, Cambridge, Mass. (1986).
IEEE First International Conference on Neural Networks, San Diego, Calif. 21-24 Jun. 1987, IEEE, A. G. Barto et al.: "Gradient Following Without Back-Propagation in Layered Networks", pp. II/629-636; see p. 629, ln 1 to p. 631 line 20.
Journal of Elct. Eng. vol. 25, No. 256, Apr. 1988 (Tokyo, JP), "Disturbance Generator Improves Recognition in Neuron Computers", pp. 74-77; see p. 75, left-hand column, line 33 to right-hand column, line 8.
IEEE ASSP Magazine, Apr. 1987, IEEE, R. O, Lippman: "An Introduction to Computing with Neural Nets", pp. 4-22.

Affiliated with

Also associated with

Rating

Memory modification of artificial neural networks does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Memory modification of artificial neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Memory modification of artificial neural networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-49523