Neural network that does not require repetitive training

Patent

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

395 21, 395 23, G06F 1518

Patent

active

055176674

ABSTRACT:
A neural network, which may be implemented either in hardware or software, is constructed of neurons or neuron circuits each having only one significant processing element in the form of a multiplier. A hidden neuron in the neural network generates an output based on the product of a plurality of functions. The neural network utilizes a training algorithm which does not require repetitive training and which yields a global minimum to each given set of input vectors.

REFERENCES:
patent: 3638196 (1972-01-01), Nishiyama
patent: 3922536 (1975-11-01), Hampel et al.
patent: 3967100 (1976-06-01), Shimomura
patent: 4660166 (1987-04-01), Hopfield
patent: 4874963 (1989-10-01), Alspecter
patent: 4912649 (1990-03-01), Wood
patent: 5046020 (1991-09-01), Filkin
patent: 5058180 (1991-10-01), Khan
patent: 5073867 (1991-12-01), Murphy et al.
patent: 5093792 (1992-03-01), Taki et al.
patent: 5159660 (1992-10-01), Lu et al.
patent: 5166539 (1992-11-01), Uchimura et al.
patent: 5220559 (1993-06-01), Tsuzuki et al.
patent: 5239594 (1993-08-01), Yoda
patent: 5251286 (1993-10-01), Wiener et al.
patent: 5263121 (1993-11-01), Melsa et al.
patent: 5265192 (1993-11-01), McCormack
patent: 5272723 (1993-12-01), Kimoto et al.
patent: 5293457 (1994-03-01), Arima et al.
patent: 5333239 (1994-07-01), Watanabe et al.
patent: 5333240 (1994-07-01), Matsumoto et al.
Keith C. Drake, "Highly-Automated, Non-Parametric Statistical Learning for Autonomous Target Recognition", Proceedings of the SPIE 20th Applied Imagery Pattern Recognition Workshop--Oct. 1991, McLean, Virginia, pp. 1-10.
Sean B. Holden and Peter J. W. Rayner, "Generalization and Learning in Volterra and Radial Basis Function Networks: A Theoretical Analysis", IEEE International Conference on Acoustics, Speech and Signal Processing, Mar. 23-26, 1992, vol. II, pp. II-273-II-276.
Jack Shandle, "Neural Networks are Ready for Prime Time", Electronic Design, Advanced Technology Series, Feb. 18, 1993, pp. 51-58.
Naohiro Toda, Ken-ichi Funahashi and Shiro Usui, "Polynomial Functions Can Be Realized by Finite Size Multilayer Feedforward Neural Networks", IEEE International Joint Conference on Neural Networks, Nov. 18-21, 1991, Singapore, vol. 1 of 3, pp. 343-348.
Richard P. Lippmann, "An Introduction to Computing with Neural Nets", IEEE ASSP Magazine, Apr. 1987, pp. 4-22.
Peter D. Varhol, "Modeling Systems with Polynomial Networks", Dr. Dobb's Journal, Sep. 1993.
AbTech Corporation, "AIM.TM. Outperforms Neural Networks and Regression!", Brochure, 1993.
Chang et al., "Polynomial and Standard Higher order Neural Network", IEEE Int. Conf. on Neural Networks, Mar.-Apr. 1993.
Manry et al., "Output Weight Optimization for the Multi-Layer Perceptron", Conf. Record of the Twenty-Sixth Asilomar Conf. on Signals, Systems and Computers, 26-28 Oct. 1992.
Malakooti et al., "An Artificial Neural Networks for Approximating Polynomial functions", IJCNN, Jun. 1992.
Hoffmann et al, "A Neural Feed Forward Network with A Ploynomial Nonlinearity", Proceedings of the IEEE-SP Workshop; 31 Aug-2 Sep. 1992.
Wei et al., "Approximation Property of Multi-Layer Neural Network (MLNN) and its Application in Nonlinear simulation", IJCNN, Jul. 1991.
Roy et al., "A Polynominal Time Algorithm for generating Neural Networks for Classification Problems", IJCNN, 1992.

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 that does not require repetitive training 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 that does not require repetitive training, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Neural network that does not require repetitive training will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFUS-PAI-O-1904731

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