Data processing: artificial intelligence – Neural network – Learning task
Reexamination Certificate
2002-09-24
2008-08-19
Holmes, Michael B (Department: 2129)
Data processing: artificial intelligence
Neural network
Learning task
Reexamination Certificate
active
07415445
ABSTRACT:
A two-class analysis system for summarizing features and determining features appropriate to use in training a classifier related to a data mining operation. Exemplary embodiments describe how to select features which will be suited to training a classifier used for a two-class text classification problem. Bi-Normal Separation methods are defined wherein there is a measure of inverse cumulative distribution function of a standard probability distribution and representative of a difference between occurrences of the feature between said each class. In addition to training a classifier, the system provides a means of summarizing differences between classes.
REFERENCES:
patent: 5649061 (1997-07-01), Smyth
patent: 5956707 (1999-09-01), Chu
patent: 6038527 (2000-03-01), Renz
patent: 6054991 (2000-04-01), Crane et al.
patent: 6101275 (2000-08-01), Coppersmith et al.
patent: 6182058 (2001-01-01), Kohavi
patent: 6182070 (2001-01-01), Megiddo et al.
patent: 6192360 (2001-02-01), Dumais et al.
patent: 6212532 (2001-04-01), Johnson et al.
patent: 6278464 (2001-08-01), Kohavi et al.
patent: 6445390 (2002-09-01), Aftosmis et al.
patent: 6701333 (2004-03-01), Suermondt et al.
patent: 6947936 (2005-09-01), Suermondt et al.
patent: 7200604 (2007-04-01), Forman et al.
patent: 7272945 (2007-09-01), Bash et al.
patent: 2002/0133668 (2002-09-01), Sherman
patent: 2002/0147546 (2002-10-01), Kanevsky et al.
patent: 2002/0194251 (2002-12-01), Richter et al.
patent: 2002/0196679 (2002-12-01), Lavi et al.
patent: 2002/0196975 (2002-12-01), Cahill et al.
Andrew McCallum, “Bow: A Toolkit for Statistical Language Modeling, Text Retrieval, Classification and Clustering”, 1998, (http://www.cs.cmu.edu/˜mccallum/bow/), Pertinant Pages: Bow and Rainbow.□□.
Entisoft, “Math Probability Class Entisoft Tools 2.0 Object Library Version 2.1 Build 208”, 1999.
Wu et al., “Fast probabilistic analysis of sequence function using scoring matrices”, Bioinformatics, vol. 16, No. 3, 2000, pp. 233-244.
Nigam et al., “Text Classication from Labeled and Unlabeled Documents using EM”, 1999, Machine Learning, , 1-34.
U.S. Appl. No. 10/354,844, filed Jan. 29, 2003, George Henry Forman.
Yang, Yiming et al. “A comparative Study in Feature S Election in Text Categorization”, Carnegie Mellon University and Verity, Inc., 9 pgs (1997).
Dietterich, thomas g., et al., “soving Multiclass Learning Problems via error-correcting output codes”, Journal of Artificial Intelligence Research 2 pp. 263-286(Jan. 1995).
Hewlett--Packard Development Company, L.P.
Holmes Michael B
LandOfFree
Feature selection for two-class classification systems does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Feature selection for two-class classification systems, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Feature selection for two-class classification systems will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-4009794