Clustered neural networks

Details Clustered neural networks Clustered neural networks

1990-10-09

1992-10-13

Fleming, Michael R.

Image analysis

Histogram processing

For setting a threshold

395 21, 382 14, G06K 962

Patent

active

051558017

ABSTRACT:
A plurality of neural networks are coupled to an output neural network, or judge network, to form a clustered neural network. Each of the plurality of clustered networks comprises a supervised learning rule back-propagated neural network. Each of the clustered neural networks are trained to perform substantially the same mapping function before they are clustered. Following training, the clustered neural network computes its output by taking an "average" of the outputs of the individual neural networks that make up the cluster. The judge network combines the outputs of the plurality of individual neural networks to provide the output from the entire clustered network. In addition, the output of the judge network may be fed back to each of the individual neural networks and used as a training input thereto, in order to provide for continuous training. The use of the clustered network increases the speed of learning and results in better generalization. In addition, clustering multiple back-propagation networks provides for increased performance and fault tolerance when compared to a single unclustered network having substantially the same computational complexity. The present invention may be used in applications that are amenable to neural network solutions, including control and image processing applications. Clustering of the networks also permits the use of smaller networks and provides for improved performance. The clustering of multiple back-propagation networks provides for synergy that improves the properties of the clustered network over a comparably complex non-clustered network.

REFERENCES:
patent: 4254474 (1981-03-01), Cooper et al.
patent: 4760604 (1988-07-01), Cooper et al.
patent: 4884194 (1989-11-01), Krol et al.
patent: 4907232 (1990-03-01), Harper et al.
patent: 4941122 (1990-07-01), Weideman
patent: 4964126 (1990-10-01), Musicus et al.
patent: 4972473 (1990-11-01), Ejiri et al.
patent: 4995040 (1991-02-01), Best et al.
patent: 5060278 (1991-10-01), Fukumizu
Lippmann, R. P., "An Introduction to Computing with Neural Nets", IEEE ASSP Mag., Apr. 1987, pp. 4-22.
Cortes et al., "A Network System for Image Segmentation", I JCNN 1989, pp. I-121-I-125.
Roth, M. W., "Survey of Neural Network Technology for Automatic Target Recognition", IEEE Trans. Neural Network's, vol. 1(1) Mar. 1990, pp. 28-43.
Lee, J., Weger, R. C., "A Hybrid Competitive Learning Backpropagation Network", The Journal of Knowledge Engineering, Spring 1990, pp. 38-43.

Affiliated with

Also associated with

Rating

Clustered 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 Clustered neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Clustered neural networks will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1307216