Unsupervised training method for a neural net and a neural net c

Details Unsupervised training method for a neural net and a neural net c Unsupervised training method for a neural net and a neural net c

1992-05-22

1995-11-21

Downs, Robert W.

395 21, 395 24, 395 241, G06F 1518

Patent

active

054695309

ABSTRACT:
Unsupervised training method for a neural net and a neural net classifier device wherein test vectors are supplied to the neural net whose operational parameters are classified in a stochastic labeling procedure by mutually correlating the net's output activations for each test vector and on the basis thereof generating weighting factors that scale the probabilities when selecting a class at random. Once the test vectors are thus classified, the operational parameters of the net are modified in order to intensify the differences among the patterns of output activations for all test vectors.

REFERENCES:
patent: 4858147 (1989-08-01), Conwell
patent: 4931868 (1990-06-01), Kadar
patent: 4972363 (1990-01-01), Nguyen et al.
patent: 4979126 (1990-12-01), Pao et al.
patent: 5067164 (1991-11-01), Denker et al.
patent: 5105468 (1992-04-01), Guyon et al.
patent: 5136686 (1992-08-01), Koza
patent: 5140530 (1992-08-01), Guha et al.
patent: 5142612 (1992-08-01), Sheirik
patent: 5142665 (1992-08-01), Bigus
patent: 5150450 (1992-09-01), Swenson et al.
patent: 5159644 (1992-10-01), Martin et al.
patent: 5179596 (1993-01-01), Weingard
patent: 5214746 (1993-05-01), Fogel et al.
patent: 5218529 (1993-06-01), Meyer et al.
patent: 5299284 (1994-03-01), Roy
A. J. Owens and D. L. Filkin; "Efficient Traing . . . of Stiff Ordinary Differential Equations"; vol. 2, pp. 381-386. Dec. 31, 1989 IJCNN.
L. A. Reed & J. T. Helferty; "A Translation/Rotation . . . via Gradient Optimization"; IEEE Int. Conf. on Systems Eng. Aug. 24, 1989 pp. 161-164.
Diamantaras et al, "An unsupervised neural model for oriented principal component extraction"; ICASSP 91, p. 1049-52 vol. 2, May 14-17, 1991.
Kosko, "Structural stability of unsupervised learning in feedback neural networks"; IEEE Transactions on Automatic Control, vol. 36 Iss. 7, p. 785-92, Jul. 1991.
R. Dubes et al., "Clustering methodologies in exploratory data analysis", Advances in Computers, vol. 19, 1980, pp. 113-228.
"Discriminant Analysis and Clustering", published in Statitical Science, vol. 4 (1989), pp. 34-69.
"A Neural Unsupervised Learning Technique", A. F. Atiya, Department of Electrical Engineering, California Institute of Technology, Pasadena, Calif. during symposium for the Official Jour. of the Int'l Neural Netowrk Soc., Sep. 6-10, 1988.
"Optimal Unsupervised Learning Multicategory Dependent Hypotheses Pattern REcognition", IEEE-IT-14, No. 3, May 1968, pp. 468-470.
"Learning To Recognize Patterns Without A Teacher", IEEE-IT-13, No. 1, Jan. 1967, pp. 57-64.

Affiliated with

Also associated with

Rating

Unsupervised training method for a neural net and a neural net c does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Unsupervised training method for a neural net and a neural net c, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Unsupervised training method for a neural net and a neural net c will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1144470