Neural network with dynamically adaptable neurons

Details Neural network with dynamically adaptable neurons Neural network with dynamically adaptable neurons

1993-05-27

1994-03-29

MacDonald, Allen R.

395 23, G06F 1518, G06G 719

Patent

active

052992853

ABSTRACT:
This invention is an adaptive neuron for use in neural network processors. The adaptive neuron participates in the supervised learning phase of operation on a coequal basis with the synapse matrix elements by adaptively changing its gain in a similar manner to the change of weights in the synapse io elements. In this manner, training time is decreased by as much as three orders of magnitude.

REFERENCES:
patent: 3950733 (1976-04-01), Cooper et al.
patent: 4829925 (1989-07-01), Peckerar et al.
patent: 4912647 (1990-03-01), Wood
patent: 4941122 (1990-07-01), Weideman
patent: 4947482 (1990-08-01), Brown
patent: 4959532 (1990-09-01), Owechko
patent: 5075871 (1991-12-01), Weidman
"Design of Parallel Hardware Neural Network Systems From Custom Analog VLSI `Building Block` Chips", Eberhardt et al., IJCNN, Jun. 18-22 1989; vol. 2.
"Parallel Distributed Processing", David Rumelhart and James McClelland, vol., 1986.
"An Introduction to Computing with Neural Network", Richard Lippmann, IEEE ASSP Mag., Apr. 1987.
"Simple Neural Optimization Networks", David Tank and John Hopfield, IEEE, 1986.
Tawel et al. "Does Neuron Learn Like The Synapse?" Feb. 15, 1989.

Affiliated with

Also associated with

Rating

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

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-799031