Data processing: artificial intelligence – Neural network – Learning task
Reexamination Certificate
2006-10-17
2009-10-06
Holmes, Michael B (Department: 2129)
Data processing: artificial intelligence
Neural network
Learning task
Reexamination Certificate
active
07599898
ABSTRACT:
The present invention is a method and an apparatus for improved regression modeling to address the curse of dimensionality, for example for use in data analysis tasks. In one embodiment, a method for analyzing data includes receiving a set of exemplars, where at least two of the exemplars include an input pattern (i.e., a point in an input space) and at least one of the exemplars includes a target value associated with the input pattern. A function approximator and a distance metric are then initialized, where the distance metric computes a distance between points in the input space, and the distance metric is adjusted such that an accuracy measure of the function approximator on the set of exemplars is improved.
REFERENCES:
patent: 5754681 (1998-05-01), Watanabe et al.
patent: 6295509 (2001-09-01), Driskell
patent: 6353814 (2002-03-01), Weng
patent: 6939670 (2005-09-01), Pressman et al.
patent: 7020631 (2006-03-01), Freeman et al.
patent: 7165037 (2007-01-01), Lazarus et al.
patent: 7214485 (2007-05-01), Belinsky et al.
patent: 7260551 (2007-08-01), Phillips
patent: 7263492 (2007-08-01), Suresh et al.
patent: 7263506 (2007-08-01), Lee et al.
patent: 7363308 (2008-04-01), Dillon et al.
patent: 7373256 (2008-05-01), Nicholson et al.
patent: 7376618 (2008-05-01), Anderson et al.
patent: 7436511 (2008-10-01), Ruchti et al.
patent: 7451065 (2008-11-01), Pednault et al.
patent: 7512508 (2009-03-01), Rajski et al.
A regression approach to equivalent bandwidth characterization in ATM networks Ramaswamy, S.; Ono-Tesfaye, T.; Gburzyuski, P.; Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, 1997. MASCOTS '97., Proceedings Fifth International Symposium on Jan. 12-15, 1997 pp. 104-109 Digital Object Identifier 10.1109/MASCOT.1997.
Combining Landsat ETM+ and terrain data for scaling up leaf area index (LAI) in eastern Amazon: an intercomparison with MODIS product Shimabukuro, Y.E.; Aragao, L.E.O.C.; Espirito-Santo, F.D.B.; Williams, M.; Geoscience and Remote Sensing Symposium, 2004. IGARSS '04. Proceedings. 2004 IEEE International vol. 3, Sep. 20-24, 2004 pp. 2050-2053.
An intelligent system for financial time series prediction combining dynamical systems theory, fractal theory, and statistical methods Castillo, O.; Melin, P.; Computational Intelligence for Financial Engineering, 1995.,Proceedings of the IEEE/IAFE 1995 Apr. 9-11, 1995 pp. 151-155 Digital Object Identifier 10.1109/CIFER.1995.495269.
International Search Report and Written Opinion for PCT/US2007/078377, copy consists of 16 unnumbered pages.
Jacob Goldberger, et al., “Neighbourhood Compenents Analysis”, Internet Citation, [Online] 2004, XP007903888, Retrieved from the internet: URL:http://www.cs.toronto.edu/{hinton/absps
ca.pdf> [retrieved on Jan. 21, 2008].
Aha D W, “Tolerating noisy, irrelevant and novel attributes in instance-based learning algorithms”, International Journal of Man—Machine Studies, Academic Press, London, GB, vol. 36, 1992, pp. 267-287, XP007903847 ISSN: 0020-7373, Section 4: “Tolerating attributes with uncertain tolerance”, in particular, subsection 4.2: “IB4: Learning attribute relevance”.
Fukunaga, Keinosuke, “Introduction to Statistical Pattern Recognition, Chapter 6 (p. 254-299)”, 1990, Academic Press, Inc., Boston 207370, XP002466163.
Weinberger, Kilian Q., Tesauro, Gerald, “Metric Learning for Kernel Regression”, Proceedings of the 11thInternational Conference on Artifical Intellegence and Statistics, [Online] Mar. 21, 2007-Mar. 24, 2007, XP007903848 Online ISBN: 0-9727358-2-8, Retrieved from the Internet: URL:http://www.stat.umn.edu/{aistat/proceedings/data/papers/077.pdf> [retrieved on Jan. 21, 2007.
Shental, Noam; Hertz, Tomer; Weinshall, Daphna; Pavel, Misha, “Adjustment Learning and Relevant Component Analysis”, Proceedings of ECCV, [Online] Jun. 2002, XP007903913, Copenhagen, DK, Retrieved from the Internet: URL:http://citeseer.ist.psu.edu/cache/papers/cs/26471/http:zSzzSzleibniz.cs.huji.ac.ilzSztrzSzacczSz2002zSzHUJI-CSE-LTR-2002-16—paper—CR01.pdf/shental02adjustment.pdf> [retrieved on Jan. 24, 2008].
Scott Cost, et al., “A Weighted Nearest Neighbor Algorithm for Learning with Symobolic Features”, Machine Learning, Kluwer Academic Publishers—Plenum Publishers, NE, vol. 10, No. 1, Jan. 1, 1993, pp. 57-78, XP019213229 ISSN: 1573-0565.
Lowe D G, “Similarity Metric Learning for A Variable-Kernel Classifier”, Internet Citation, [Online] Nov. 25, 1993, XP007903889, retrieved from the Internet: http://citeseer.ist.psu.edu/cache/papers/cs/286/http:zSzzSzwww.cs.ubc.cazSzspiderzSzlowezSzpaperszSzneural95.pdf/lowe95similarity.pdf> [retrieved on Jan. 21, 2008].
Tesauro Gerald J.
Weinberger Kilian Q.
Holmes Michael B
International Business Machines - Corporation
LandOfFree
Method and apparatus for improved regression modeling 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 improved regression modeling, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for improved regression modeling will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4093891