Multi-layer neural network employing multiplexed output neurons

Details Multi-layer neural network employing multiplexed output neurons Multi-layer neural network employing multiplexed output neurons

1990-12-28

1992-02-11

Hudspeth, David

Electrical transmission or interconnection systems

Nonlinear reactor systems

Parametrons

307243, 395 24, G06C 712

Patent

active

050878263

ABSTRACT:
A multi-layer electrically trainable analog neural network employing multiplexed output neurons having inputs organized into two groups, external and recurrent (i.e., feedback). Each layer of the network comprises a matrix of synapse cells which implement a matrix multiplication between an input vector and a weight matrix. In normal operation, an external input vector coupled to the first synaptic array generates a Sigmoid response at the output of a set of neurons. This output is then fed back to the next and subsequent layers of the network as a recurrent input vector. The output of second layer processing is generated by the same neurons used in first layer processing. Thus, the neural network of the present invention can handle N-layer operation by using recurrent connections and a single set of multiplexed output neurons.

REFERENCES:
patent: 4760346 (1988-07-01), Kultgen et al.
patent: 4873661 (1989-10-01), Tsividis
patent: 4926064 (1990-05-01), Tapang
patent: 4951239 (1990-08-01), Andes et al.
patent: 4972157 (1990-11-01), Mayal
patent: 4972363 (1990-11-01), Nguyen et al.
patent: 4985703 (1991-01-01), Kaneyama
patent: 5039871 (1991-08-01), Engeler
Hopfield & Tank, "Computing with Neural Networks: A Model" Science, vol. 233, pp. 625-633, Aug. 1986.
Graf & Jackel, "Analog Electronic Neural Network Circuits" IEEE Circuits & Devices, Jul. 1989, pp. 44-50.
"Time-Multiplicated Analogue Circuit For Implementing Artificial Neural Networks", Electronics Letters, vol. 24, No. 23, Nov. 1988, pp. 1413-1414.

Affiliated with

Also associated with

Rating

Multi-layer neural network employing multiplexed output 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 Multi-layer neural network employing multiplexed output neurons, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multi-layer neural network employing multiplexed output neurons will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-783352