Method and apparatus for using a neural network to extract an op

Details Method and apparatus for using a neural network to extract an op Method and apparatus for using a neural network to extract an op

1995-04-18

1997-12-09

Moore, David K.

395 22, 395 24, 395 21, G06F 1518

Patent

active

056968825

ABSTRACT:
Method and apparatus for selecting an optimized subset of trajectories from an available class of potential trajectories in a velocimetry application. In an exemplary method, a neural network is constructed wherein each neuron in the network represents a trajectory in the overall class. A binary output of each neuron indicates whether the object represented by the neuron is to be selected. In the exemplary method, the neural network is in an initially converged state. The network is then alternately excited and constrained so that it settles to additional converged states. During excitation, correction factors including a parameter-optimizing term are applied to neuron input potentials. During constraint, the parameter-optimizing terms are interrupted. Each time the network converges, the outputs of the neurons in the network are decoded to establish a subset of trajectories to be selected, and a value for an optimization parameter associated with the established subset is computed. The excitation and constraint phases are repeated in an attempt to establish subsets of trajectories having superior optimization parameter values. Once the excitation and constraint phases have been repeated a suitable number of times, the trajectories identified in a subset of objects having a superior optimization parameter value are selected. In exemplary embodiments, neurons are updated in a novel block-sequential fashion.

REFERENCES:
patent: 4918618 (1990-04-01), Tomlinson, Jr.
patent: 5195170 (1993-03-01), Eberhardt
patent: 5210798 (1993-05-01), Ekchian et al.
patent: 5504841 (1996-04-01), Tani
Churchland et al., "The Computational Brain," The MIT Press, Cambridge, MA, Dec. 30, 1992.
Chuanyi and Psaltis (1991) "The Capacity of a Two Layer Network with Binary Weights," Neural Networks, 1991 IEEE International Conference (Seattle), vol. II p. 127, Dec. 1991.
Jagota (1993) "Optimization by Reduction to Maximal Clique,"Neural Networks, 1993 IEEE International Conference, p. 1526, Dec. 1993.
Jagota et al. (1994) "Information Capacity and Fault Tolerance of Binary Weights Hopfield Nets," Neural Networks, 1994 IEEE International Conference, vol. II, p. 1044, Dec. 1994.
Yuan and Chen (1990) "Neural Net Decoders for Some Block Codes," IEE Proceedings. Part I: Communications, Speech, and Vision, vol. 137, Pt I, No. 5, p. 309, Oct. 1990.
van Hemmen and Kuhn (1986) "Nonlinear Neural Nets," Physical Review Letters, vol 57, No. 7, p. 913, Dec. 1986.
Hertz et al. "Introduction to the Theory of Neural Computation," Addison-Wesley Publishing Company, Mar. 1992, Dec. 1991.
Optimal Control With A Recurrent Neural Network And A Priori Knowledge Of The System--Hoshino, et al.--1991 IEEE International Joint Conference On Neural Networks--vol. 1, 18 Nov. 1991, Singapore--pp. 226-231.

Affiliated with

Also associated with

Rating

Method and apparatus for using a neural network to extract an op does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Method and apparatus for using a neural network to extract an op, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for using a neural network to extract an op will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-1614803