Boots – shoes – and leggings
Patent
1996-02-15
1998-04-28
Voeltz, Emanuel Todd
Boots, shoes, and leggings
705 35, 705 36, 395 20, 364420, 364421, 364422, G06F 1760
Patent
active
057453837
ABSTRACT:
A method and apparatus for predicting whether a specified threshold is likely to be exceeded for a specified predictor, based on preexisting information about related predictors and associated outcomes. If each predictor vector has n components, and the value of the outcome associated with m such predictor vectors is known, then the present invention shows how to guess the outcome associated with another predictor vector in fewer computational steps and more accurately than any previously known method. The invention is of great use in any situation where it is useful to be able to decide between two alternatives. More generally, the invention can be applied to problems where whether to adopt one alternative or the other depends on the value of a threshold.
REFERENCES:
patent: 5444819 (1995-08-01), Negishi
patent: 5479361 (1995-12-01), Kurtberg et al.
patent: 5487001 (1996-01-01), Neff
patent: 5519605 (1996-05-01), Cawfield
patent: 5546329 (1996-08-01), Kurtsberg et al.
patent: 5568378 (1996-10-01), Wojsznis
patent: 5608620 (1997-03-01), Lundgren
patent: 5627768 (1997-05-01), Uhlmann et al.
B Boser, I Guyon, V Vapnik, "A Training Algorithm for Optimal Margin Classifiers", Proceedings of the 5th ACM Conference on Computational Learning Theory, Pittsburgh PA, 1992.
Tom Bylander, "Learning Linear Threshold Functions in the Presence of Classification Noise", Proceedings of the 7th ACM Conference on Computational Learning Theory, New Brunswick NJ, 1994.
Michael Kearns, "Efficient Noise-Tolerant Learning From Statistical Queries", Proceedings of the 25th ACM Symposium on the Theory of Computing, 1993.
HSM Coxeter, "The Functions of Schlafli and Lobatcshefsky", Twelve Geometric Essays, Feffer & Simmons, Southern Illinois Press, 1968, pp. 13-29.
K Hoffgen, H Simon, "Robust Trainability of Single Neurons", Proceedings of the 5th ACM Conference on Computational Learning Theory, Pittsburgh PA, 1992.
Nick Littlestone, "Redundant Noisy Attributes, Attribute Errors, and Linear Threshold Learning Using Winnow", Proceedings of the 4th ACM Conference on Computational Learning Theory, Santa-Cruz CA 1991.
L. Schl.ang.fli, "On the multiple integral .intg. .intg. . . . .intg. dx dy . . . dz whose limits are p.sub.1 =a.sub.1 x+b.sub.1 y+ . . . +h.sub.1 z>0,p.sub.2 >0, . . . ,p.sub.n >0, and x.sup.2 +y.sup.2 + . . . +z.sup.2 <1", Quarterly Journal of Math 3, 1860, pp. 54-68, 97-108.
Assouad Patrick
Todd Voeltz Emanuel
LandOfFree
Method and apparatus for efficient threshold inference 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 efficient threshold inference, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for efficient threshold inference will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-1539060