Patent
1994-08-11
1996-07-09
Downs, Robert W.
395 27, G06F 1518
Patent
active
055353096
ABSTRACT:
A neural network provides both linearly separable and non-linearly separable logic operations, including the exclusive-or operation, on input signals in a single layer of circuits. The circuit weights the input signals with complex weights by multiplication and addition, and provides weighted signals to a neuron circuit (a neuron body or some a) which provides an output corresponding to the desired logical operation.
REFERENCES:
patent: 3735403 (1973-05-01), Sykes
patent: 4237737 (1980-12-01), Nitadori
patent: 4747150 (1988-05-01), Knutsson et al.
patent: 4904881 (1990-02-01), Castro
patent: 4954963 (1990-09-01), Penz et al.
patent: 4979124 (1990-12-01), Sachse et al.
patent: 4979126 (1990-12-01), Pao et al.
patent: 4994982 (1991-02-01), Duranton et al.
patent: 4999525 (1991-03-01), Park et al.
patent: 5040214 (1991-08-01), Grossberg et al.
patent: 5043913 (1991-08-01), Furtani
patent: 5052043 (1991-09-01), Gabroski
patent: 5075889 (1991-12-01), Jousselin et al.
patent: 5083044 (1992-01-01), Mead et al.
patent: 5083285 (1992-01-01), Shima et al.
patent: 5087826 (1992-02-01), Holler et al.
patent: 5097141 (1992-03-01), Leivian et al.
patent: 5103431 (1992-04-01), Freeman et al.
patent: 5131072 (1992-07-01), Yoshizawa et al.
patent: 5161203 (1992-11-01), Buckley
patent: 5261035 (1993-11-01), Adler
patent: 5355436 (1994-10-01), Shin et al.
De Sovigny et al, "Realization of Boolean Functions Using A Pulse Coded Non", 1992 IEEE Int'l Symposium on Circuits & Systems, May 10-13 1992, pp. 2229-2231 vol. 5.
Hirose, "Dynamics of Fully Complex-valved Neural Networks", Electronics Letters, Jul. 30, 1992 vol. 28 No. 16.
Leung and Haykin, "The Complex Backpropagation Algorithm", IEEE Transactions on Signal Processing, vol. 39, No. 9, 1991, Sep. 1991, pp. 2101-2104.
Benvenuto et al., "A Comparison between Real and Complex Valued Neural Networks in Communication Applications", Artificial Neural Networks, Elsevier Science Publishers, BV (North-Holland), pp. 1177-1180, (1991).
Little et al, "Generalization of the Backpropagation Neural Network Learning Algorithm to Permit Complex Weights", Applied vol. 29, No. 11, Apr. 10, 1990, pp. 1591-1592.
Kim and Guest, "Modification of Backpropagation Networks for Complex-Valued Signal Processing in Frequency Domain," IJCNN, Jun. 1990, pp. III-27-III-31.
Widrow et al., "The Complex LMS Algorithm", Proceedings of the IEE, Apr. 19, 1975, pp. 719-720.
Rumelhart et al., "Learning Representations by Backpropagating Errors", Nature No. 323, pp. 533-536, 1986.
Rumelhart et al., "Learning Internal Representations by Error Propagation", from Parallel Distributed Processing: Explorations in Micro Structures of Cognition, vo. 1, MIT Press, 1986, pp. 318-362.
W. McCulloch and W. Pitts, "A Logical Calculus of the Ideas Immanent in Nervous Activity", Bulletin of Mathematical Biophysics, vol. 5, 1943, pp. 115-133.
J. Anderson and E. Rosenfeld, "Neurocomputing: Foundations of Research", The MIT Press, 1988.
R. Hecht-Nielson, "Neurocomputing", Addison-Wesley, 1989, pp. 17-18.
Widrow, et al., "Learning Phenomena in Layered Neural Networks", IEEE First Inter. Conf. on Neural Networks, 1987, pp. II-411-II429.
Lippmann, "An Introduction to Computing With Neural Nets", IEEE ASSP Magazine, Apr. 1987, pp. 4-22.
Shin Yong-Chul
Sridhar Ramalingam
Downs Robert W.
The Research Foundation, State University of New York at Buffalo
LandOfFree
Single layer neural network circuit for performing linearly sepa does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Single layer neural network circuit for performing linearly sepa, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Single layer neural network circuit for performing linearly sepa will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1875022