Artificial neural network (ANN) classifier apparatus for selecti

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 24, 395 27, G06F 900, G06F 1546

Patent

active

054795729

ABSTRACT:
An artificial neural network (ANN) classifier provides a series of outputs indicative of a series of classes to which input feature vectors are classified. The ANN provides only one output for each input feature vector to partition said input into one class. The one output of the classifier is coupled to the interrupt input of an associated digital computer or CPU. Upon receipt of the output, the CPU immediately interrupts a main program and executes an interrupt service routine which is triggered by the output of the classifier. In this manner, the CPU is immediately accessed in the interrupt mode by the transition of one of the output class processing elements when activated.

REFERENCES:
patent: 4964032 (1990-10-01), Smith
patent: 5001631 (1991-03-01), Castelaz
patent: 5052043 (1991-09-01), Gaborski
patent: 5107454 (1992-04-01), Niki
patent: 5170463 (1992-12-01), Fujimoto et al.
patent: 5175796 (1992-12-01), Refregier et al.
patent: 5239594 (1993-08-01), Yoda
patent: 5247584 (1993-09-01), Krogmann
patent: 5274743 (1993-12-01), Imondi et al.
Lin et al, "Microprocessors", The Institute of Electrical and Electronic Engineers, Inc., IEEE 1977.
Lippmann et al, "Pattern Classification Using Neural Networks", IEEE Communication Magazine, Nov. 1989.
"Networks for Approximation and Learning", Proceedings of the IEEE, vol. 78, No. 9, Sep. 1990, pp. 1481-1497.
"30 Years of Adaptive Neural Networks: Perceptron, Madaline, & Backpropagation", Widrow et al., Proceedings of the IEEE, vol. 78, No. 9, Sep. 1990, pp. 1415-1442.
"The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network", Carpenter et al., Computer, Mar. 1988, pp. 77-88.
"An Optimal Self-Organizing Pattern Classifier", Mekkaoui et al., Proceedings of the Int'l Joint Conference on Neural Networks, vol. I, Jan. 15-19, 1990, Washington, D.C., pp. 447-450.
"A New Approach to Clustering", Wilson et al., Pattern Recognition, vol. 23 No. 12, pp. 1413-1425, 1990.
"Counterpropagation Networks", Hecht-Nielsen, IEEE First Int'l Conference on Neural Networks, vol. II, Jun. 21-24, 1987, San Diego, Calif., pp. 19-32.
"A deterministic annealing approach to clustering", Rose et al. Pattern Recognition Letters, Sep. 1990, pp. 589-594.
"Self-Organization and Associative Memory", Kohonen, Springer-Verlag, 3rd ed. Berlin, Heidelberg, Germany, 1989, pp. 68-81.
"Spectral Clustering with Neural Networks for Application to Multispectral Remote Sensing of Minerals", Breitkopf et al., Proceedings of the First Annual INNS Meeting, Boston, Mass., Sep. 6-10, 1988, p. 14.
"Fish Detection and Classification Using a Neural-Network Based Active Sonar System-Preliminary Results", Ramani et al, Proceedings of the International Joint Conference on Neural Networks, vol. II, Washington, D.C., Jan. 15-19, 1990, pp. 527-530.
"Learned Classification of Sonar Targets Using a Massively Parallel Network", Gorman et al., IEEE Transactions on Acoustics, Speech, and Signal Processing, vol. 36, No. 7, Jul. 1988, pp. 1135-1140.
"Radar Signal Categorization Using a Neural Network", Anderson et al., Proceedings of the IEEE, vol. 78, No. 10, Oct. 1990, pp. 1646-1657.

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

Artificial neural network (ANN) classifier apparatus for selecti does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Artificial neural network (ANN) classifier apparatus for selecti, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Artificial neural network (ANN) classifier apparatus for selecti will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1375683

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