Spectral kernels for learning machines

Details Spectral kernels for learning machines Spectral kernels for learning machines

2005-09-13

2005-09-13

Hirl, Joseph P. (Department: 2121)

Data processing: artificial intelligence

Machine learning

C706S014000, C706S046000

Reexamination Certificate

active

06944602

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:
Nello Cristianini et al, Support Vector Machines, Mar. 2000, Cambridge University Press, First Published, all but particularily 11, 30, 33, 36, 94, 151, 156-159, 169.
F. R. K. Chung et al, A near optimum algorithm for edge separators (Preliminary Version), 1994, ACM, 0-89791-663-8/94/0005.
Fan R. K. Chung, Specral Graph Theory, 1997, AMS, ISBN 0-821-80315-8.
Francois Fouss et al, Some novel ways of computing dissimilarities between nodes of a graph, with application to collaborative filtering, comtemporary, Unite ISYS/IAG.

Affiliated with

Also associated with

Rating

Spectral kernels for learning machines does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Spectral kernels for learning machines, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Spectral kernels for learning machines will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3414718