Method of using kernel alignment to extract significant...

Details Method of using kernel alignment to extract significant... Method of using kernel alignment to extract significant...

2007-11-20

2007-11-20

Hirl, Joseph P (Department: 2129)

Data processing: artificial intelligence

Machine learning

C706S014000, C706S046000

Reexamination Certificate

active

11225251

ABSTRACT:
The spectral kernel machine combines kernel functions and spectral graph theory for solving problems of machine learning. The data points in the dataset are placed in the form of a matrix known as a kernel matrix, or Gram matrix, containing all pairwise kernels between the data points. The dataset is regarded as nodes of a fully connected graph. A weight equal to the kernel between the two nodes is assigned to each edge of the graph. The adjacency matrix of the graph is equivalent to the kernel matrix, also known as the Gram matrix. The eigenvectors and their corresponding eigenvalues provide information about the properties of the graph, and thus, the dataset. The second eigenvector can be thresholded to approximate the class assignment of graph nodes. Eigenvectors of the kernel matrix may be used to assign unlabeled data to clusters, merge information from labeled and unlabeled data by transduction, provide model selection information for other kernels, detect novelties or anomalies and/or clean data, and perform supervised learning tasks such as classification.

REFERENCES:
patent: 5587922 (1996-12-01), Hendrickson et al.
patent: 5747810 (1998-05-01), Schotland
patent: 5758653 (1998-06-01), Schotland
patent: 5762607 (1998-06-01), Schotland
patent: 5787888 (1998-08-01), Schotland
patent: 6038197 (2000-03-01), Sitton et al.
patent: 6128608 (2000-10-01), Barnhill
patent: 6157921 (2000-12-01), Barnhill
patent: 6427141 (2002-07-01), Barnhill
patent: 6658395 (2003-12-01), Barnhill
patent: 6714925 (2004-03-01), Barnhill et al.
patent: 6760715 (2004-07-01), Barnhill et al.
patent: 6789069 (2004-09-01), Barnhill et al.
patent: 6882990 (2005-04-01), Barnhill et al.
patent: 6944602 (2005-09-01), Cristianini
Nello Cristianini et al, An Introduction to Support Vector Machines, Mar. 2000, University of Cambridge, Cover and title page.
Nello Cristianini et al, On Kernel-Target Alignment, Dec. 2001, MIT Press, 7.
Nello Cristianini, Spectral Kernel Methods for Clustering, Dec. 2001, MIT Press, 7.
Fernando Perez-Cruz et al, Kernel Methods and their Potential Use in Signal Processing, 2004, IEEE, 1-19.
Gang Wu et al, KBA: Kernel Boundary Alignment Considering Imbalanced Data Distribution, 2005, IEEE, 1-13.
Nello Cristianini et al., An Introduction to Support Vector Machines and Other Kernel Based Learning Methods, Cambridge, 1997, 93, 94.
F.R.K. Chung, et al., “A Near Optimum Algorithm for Edge Spearators (Preliminary Version)”, 1994, ACM, 0-89791-663-8/94/0005.
Fan R.K. Chung,Spectral Graph Theory, 1997, AMS, ISBN 0-821-80315-8 (review only).
X. S. Zhou, “Comparing Discriminating Transformations and SVM for Learning during Multimedia Retrieval”, 2001, ACM 1-581 13-394-4/01/0009 pp. 137-145.
M. Meilå, “Data Centering in Feature Space”, 9thInternational Workshop on Artificial Intelligence and Statistics, Jan. 2003.
N. Cristianini, et al., “Spectral Kernel Methods for Clustering”, Poster Presentation,Advances in Neural Information Processing Systems 2001(“NIPS01”), MIT Press, Dec. 3-8, 2001.
N. Cristianini, et al., “On Kernel-Target Alignment”, Spotlight Presentation,Advances in Neural Information Processing Systems 2001(“NIPS01”), MIT Press, Dec. 3-8, 2001.
G. Wu & E.Y. Chang, “Class-Boundary Alignment for Imbalanced Dataset Learning”,Workshop on Learning from Imbalanced Datasets II, ICML, Washington, D.C., 2003.
F. Peréz-Cruz & O. Bousquet, “Kernel Methods and their Potential Use in Signal Processing”,IEEE Signal Processing Magazine, (2004) 21:3, pp. 57-65.
X. Zhu, et al., “Nonparametric Transforms of Graph Kernels for Semi-Supervised Learning”,Advances in Neural Information Processing Systems 2004(“NIPS04”), MIT Press, 2005.
G.G. Wu & E.Y. Chang, “KBA: Kernel boundary Alignment Considering Imbalanced Data Distribution”,IEEE Transactions on Knowledge and Data Engineering(2005) 17:6, pp. 786-795.

Affiliated with

Also associated with

Rating

Method of using kernel alignment to extract significant... 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 of using kernel alignment to extract significant..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method of using kernel alignment to extract significant... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3810341