Apparatus for classifying and storing connection coefficients fo

Details Apparatus for classifying and storing connection coefficients fo Apparatus for classifying and storing connection coefficients fo

1991-04-18

1996-02-06

Downs, Robert W.

395 24, G06F 1518, G03B 4202

Patent

active

054901642

ABSTRACT:
An apparatus for storing weight coefficients for a multi-layer neural network is disclosed, wherein information representing connection coefficients is stored which represent strengths of connections between neurons of a multi-layer neural network constituted of an input layer, an intermediate layer, and an output layer, each of the input layer, the intermediate layer, and the output layer being composed of at least a single neuron. The apparatus for storing weight coefficients for a multi-layer neural network is provided with a device for classifying connections, which classifies the connections as having a high degree of connection or having a low degree of connection by comparing the connection coefficients with a predetermined threshold value, and which classifies the connections on the input side of each of the neurons as having a low degree of connection in cases where all of the connections on the output side of each said neuron have been classified as having a low degree of connection, and a storage device for storing information representing the connection coefficients of the connections, which have been classified as having a high degree of connection, and information concerning the corresponding table, which indicates whether the connections between the neurons have been classified as having a high degree of connection or having a low degree of connection by the device for classifying connections.

REFERENCES:
patent: 4912649 (1990-03-01), Wood
patent: 5195169 (1993-03-01), Kamiya et al.
Sietsma et al., "Neural Net Pruning-Why and How", IEEE Intl. Conf. Neural Networks, Jul. 1988, I, 325-333.
Karnin, E. D., "A Simple Procedure for Pruning Back-Propagation Trained Neural Networks", IEEE Trans. Neural Networks, Jun. 1990, 239-242.
Montana et al., "Training Feedforward Neural Networks Using Genetic Algorithms", IJCAI-89, Aug. 1989, 762-767.
McClelland et al., Explorations in Parallel Distributed Processing, MIT Press., 1988, pp. 1-3, 121-150.
Mozer et al., "Skeletonization: A Technique for Trimming The Fat From a Network via Relevance Assessment", from Advances in Neural Info. Processing Systems I, 1989, pp. 107-115.
Hanson et al., "Comparing Biases for Minimal Network Construction with Back-Propagation", from Advances in Neural Info. Processing Systems I, 1989, pp. 177-185.
Baum, E. B., "On the Capabilities of Multilayer Perceptions", Jour. of Complexity 4, 1988, 193-215.
Fresler, et al., "A Weight Discretization Paradigm for Optical Neural Networks", SPIE vol. 1281 Optical Interconnections and Networks, 1990, Mar. 164-173.

Affiliated with

Also associated with

Rating

Apparatus for classifying and storing connection coefficients fo does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Apparatus for classifying and storing connection coefficients fo, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Apparatus for classifying and storing connection coefficients fo will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2180624