Patent
1990-10-01
1992-09-22
Fleming, Michael R.
395 21, 395 24, G06F 1518, G06F 1546
Patent
active
051504502
ABSTRACT:
An artificial neural network has a plurality of output circuits individually perturbable for memory modification or learning by the network. The network has a plurality of synapses individually connecting each of a plurality of inputs to each output circuit. Each synapse has a weight determining the effect on the associated output circuit of a signal provided on the associated input, and the synapse is addressable for selective variation of the weight. A perturbation signal is provided to one input, while data signals are provided to others of the inputs, so that perturbation of each output circuit may be controlled by varying the weights of a set of the synapses connecting the perturbation signal to the output circuits. An output circuit may be selected for perturbation by loading an appropriate weight in the synapse connecting the perturbation signal to the output circuit while zeroing the weights of the synapses connecting the perturbation signal to other output circuits. Where the weights are provided by devices incapable of repeated cycles of zeroing and reloading, each synapse connecting the perturbation intput to an output circuit has an addressable switch which is closed for perturbation of this output circuit and which is open at other times. Perturbations of different output circuits may be balanced by varying the weights of the set of synapses connected to the perturbation input or by varying the weights of another set of the synapses connected to one of inputs which receives a balancing signal.
REFERENCES:
patent: 4773024 (1988-09-01), Faggin et al.
patent: 4874963 (1990-10-01), Alspector
patent: 4951239 (1990-08-01), Andes et al.
Alspector, "Neural-Style Microsystems That Learn", IEEE Communications Maine, Nov. 1989, pp. 29-36.
McClelland et al., Explorations in Parallel Distributed Processing, MIT Press, 1988, pp. 121-160.
Welles et al., "An Electrically Trainable Artifical Neural Network (ETANN) with 10240 Floating Gate Synposes", Proc. Intl. Conf. in Neural Networks, 1989, II-191-196.
Mark Hollar, Simon Tam, Hernan Castro, and Ronald Benson, "An Electrically Trainable Artificial Neural Network (ETANN) with 10240 `Floating Gate` Synapses"; International Joint Conference on Neural Networks; Washington, D.C.; Jun. 18-20, 1989; vol. II, pp. 191-196.
Andes David K.
Barbieri James F.
Licklider Robert A.
Swenson Richard M.
Witcher Donald H.
Church Stephen J.
Downs Robert W.
Fleming Michael R.
Forrest, Jr. John L.
Sliwka Melvin J.
LandOfFree
Method and circuits for neuron perturbation in artificial neural 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 and circuits for neuron perturbation in artificial neural, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and circuits for neuron perturbation in artificial neural will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1076050