Patent
1992-03-02
1993-12-14
Fleming, Michael R.
395 23, G06F 1518
Patent
active
052710904
ABSTRACT:
Higher operational speed is obtained without sacrificing computational accuracy and reliability in a neural network by interchanging a computationally complex nonlinear function with a similar but less complex nonlinear function in each neuron or computational element after each neuron of the network has been trained by an appropriate training algorithm for the classifying problem addressed by the neural network. In one exemplary embodiment, a hyperbolic tangent function is replaced by a piecewise linear threshold logic function.
REFERENCES:
patent: 4777613 (1988-10-01), Shahan et al.
patent: 4870606 (1989-09-01), Sasahara
patent: 4893255 (1990-01-01), Tomlinson, Jr.
patent: 4899302 (1990-02-01), Nakayama
patent: 4912649 (1990-03-01), Wood
patent: 4941122 (1990-07-01), Werdeman
patent: 5067164 (1991-11-01), Denker et al.
McClelland et al., Explorations in Parallel Distributed Processing, MIT Press, 1988, pp. 1-3, 68-75, 97-108, 121-150, 246, 251.
Fu et al., "A Universal Digital VLSI Design for Neural Networks", IJCNN, Jun. 1989.
Kung, S. Y., Hwang J. N., "A Unifying Algorithm/Architecture for Artificial Neural Networks", from Intl. Conf. on Acoustics, Speech, and Signal Processing, vol. 4, 1989, pp. 2505-2508.
Guez, A. et al., "On the Stability, Storage Capacity, and Design of Nonlinear Continuous Neural Networks", from IEEE Transactions on Systems, Man, and Cybernetics, vol. 18 No. 1, 1988, pp. 80-87.
D. E. Rumelhart et al., Parallel Distr. Proc.: Explorations in Microstructure of Cognition, vol. 1, 1986, "Learning Internal Representations by Error Propagation", pp. 318-362.
R. P. Lippmann, IEEE ASSP Magazine, vol. 4, No. 2, Apr. 1987, "An Introduction to Computing with Neural Nets":, pp. 4-22.
Y. LeCun, Connectionism in Perspective, R. Pfeifer, Z. Schreter, F. Fogelman, L. Steels, (Eds.), 1989, "Generalization and Network Design Strategies", pp. 143-155.
Y. LeCun et al., IEEE Comm Magazine, Nov. 1989, "Handwritten Digit Recognition: Applications of Neural . . . ", pp. 41-46.
AT&T Bell Laboratories
Downs Robert W.
Fleming Michael R.
Ranieri Gregory C.
LandOfFree
Operational speed improvement for neural network does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Operational speed improvement for neural network, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Operational speed improvement for neural network will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1712630