Neural network system adapted for non-linear processing

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 11, 395900, 395 51, 395 61, G06F 1518, G06F 944

Patent

active

054025192

ABSTRACT:
A neural network system includes a qualitative evaluation section, a neural network section, a quantifying section and a display section. The qualitative evaluation section qualitatively analyzes an unknown data supplied thereto, and normalizes the result of analysis within a predetermined range. The neural network section having a neural network with plural neurons computes the network output data from the normalized unknown data produced by the qualitative evaluation section. Each neuron is connected to plural other neurons through synapses, each of which is assigned an individual weight coefficient. Each neuron is adapted to output an output function value assigned thereto associated with the total sum of the products of the output from the neurons connected thereto and the synapse weight coefficient. The quantifying section quantifies the network output data to produce desired data. The desired data thus produced is displayed on the display section.

REFERENCES:
patent: 5014327 (1991-05-01), Potter et al.
patent: 5091864 (1992-02-01), Baji et al.
patent: 5159660 (1992-10-01), Lu et al.
patent: 5175797 (1992-12-01), Funabashi et al.
patent: 5195169 (1993-03-01), Kamiya et al.
patent: 5220373 (1993-06-01), Kanaya
Eppler, W., "Implementation of Fuzzy Production Systems with Neural Networks," Parallel Processing in Neural Systems and Computers, 1990, 249-252.
Kamisaka et al., "Algorithm of Pattern Recognition and Learning", Bunichi Sougou Shuppan Co., Ltd.
Lippmann, R. P., "An Introduction to Computing with Neural Nets," IEEE ASSP Magazine, Apr. 1987, 4-20.
Keller et al., "Fuzzy Logic Inference Neural Networks," SPIE vol. 1192 Intelligent Robots and Computer Vision, 1989, 582-591.
Johnson, R. C., "Japan clear on fuzzy-neural link," Electronic Engineering Times, Aug. 20, 1990, 1, 16.
Berenji, H., "Neural networks and Fuzzy Logic in Intelligent Control," Proc. 5th IEEE Intl. Symp. on Intelligent Control, Sep. 1990, 916-920.
Amano, Akio, et al. "On the Use of Neural Networks and Fuzzy Logic in Speech Recognition," IJCNN International Joint Conference on Neural Networks, Jun. 19, 1989, pp. 301-305.
Hutchinson, R. A. and W. J. Welsh, "Comparison of Neural Networks and Conventional Techniques for Feature Location in Facial Image," First IEE International Conference on Artificial Neural Networks, Oct. 16, 1989, pp. 201-205.
Mascia, Antoine H. And Rokuya Ishii, "Neural Net Implementation on Single-Chip Digital Signal Processor," IECON89: 15th Annual Conference of IEE Industrial Electronics Society, Nov. 6, 1989, pp. 764-769.
Perfetti, R., "L.sub.1 Normalisation in Neural Networks Using Parallel Automatic Level Control," Electronics Letters, Jan. 181, 990, pp. 82-84.

LandOfFree

Say what you really think

Search LandOfFree.com for the USA inventors and patents. Rate them and share your experience with other people.

Rating

Neural network system adapted for non-linear processing 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 system adapted for non-linear processing, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network system adapted for non-linear processing will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-2257765

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.