Patent
1991-06-27
1994-05-31
MacDonald, Allen R.
395 24, G06F 1518
Patent
active
053176758
ABSTRACT:
A neural network includes an input layer composed of a plurality of cells receiving respective components of an input vector, an output layer composed of a plurality of cells representing attribute of the input vector, and an intermediate layer composed of a plurality of cells connected to all the cells of the input and output layers for producing a mapping to map a given input vector to its correct attribute. A learning method utilizing such neural network is carried out by image projecting the input vector into the partial dimensional space by a projection image operating means preliminarily prepared and by storing a coupling vector on the image projection space as well as the threshold and attribute vector.
REFERENCES:
patent: 4326259 (1982-04-01), Cooper et al.
patent: 4933872 (1990-06-01), Vandenberg et al.
patent: 5031154 (1991-07-01), Watanabe
patent: 5033006 (1991-07-01), Ishizuka et al.
patent: 5046020 (1991-09-01), Filkin
patent: 5093899 (1992-03-01), Hiraiwa
patent: 5107454 (1992-04-01), Niki
patent: 5129039 (1992-07-01), Hiraiwa
patent: 5131072 (1992-07-01), Yoshizawa et al.
patent: 5140530 (1992-08-01), Guha et al.
Sebestyen, "Decision-Making Processes in Pattern Recognition," MacMillan, 1962, pp. 40-43, 47-53, 103, 108-112.
Le Cun et al., "Handwritten Digital Recognition: Applications of Neural Network Chips and Automated Learning", IEEE Communications Magazine, 1989.
Anton, "Elementary Linear Algebra," Wiley, 1981, pp. 182-187.
Wasserman, "Neural Networks, Part 2", IEEE Expert 1988.
Psaltis et al., "Optoelectronic Implementations of Neural Networks", IEEE Communications Magazine, Nov. 1989.
Lippman, et al., "Pattern Classification Using Neural Networks", IEEE Comm. Magazine, Nov. 1989.
A Neural Model for Category Learning, Douglas L. Reilly et al., Biological Cybernetics, Spring-Verlag 1982, pp. 35-41.
Learning System Composed of Multiple Neural Network Models, Nestor Inc., (Nestor Learning System) (no English translation available).
Davis George
Kabushiki Kaisha Toshiba
MacDonald Allen R.
LandOfFree
Neural network pattern recognition learning method does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Neural network pattern recognition learning method, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network pattern recognition learning method will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1634164