Exponential priors for maximum entropy models

Details Exponential priors for maximum entropy models Exponential priors for maximum entropy models

2007-05-15

2007-05-15

Hoff, Marc S. (Department: 2857)

Data processing: measuring, calibrating, or testing

Measurement system

Statistical measurement

C702S180000, C702S182000, C702S184000, C709S206000

Reexamination Certificate

active

11186318

ABSTRACT:
The subject invention provides for systems and methods that facilitate optimizing one or mores sets of training data by utilizing an Exponential distribution as the prior on one or more parameters in connection with a maximum entropy (maxent) model to mitigate overfitting. Maxent is also known as logistic regression. More specifically, the systems and methods can facilitate optimizing probabilities that are assigned to the training data for later use in machine learning processes, for example. In practice, training data can be assigned their respective weights and then a probability distribution can be assigned to those weights.

REFERENCES:
patent: 6125362 (2000-09-01), Elworthy
patent: 6161130 (2000-12-01), Horvitz et al.
patent: 6304841 (2001-10-01), Berger et al.
patent: 6553358 (2003-04-01), Horvitz
patent: 6606620 (2003-08-01), Sundaresan et al.
patent: 6609094 (2003-08-01), Basu et al.
patent: 6697769 (2004-02-01), Goodman et al.
patent: 2003/0105638 (2003-06-01), Taira
patent: 2003/0126102 (2003-07-01), Borthwick
patent: 2004/0260992 (2004-12-01), Goodman et al.
patent: 2005/0096907 (2005-05-01), Bacchiani et al.
Chen & Rosenfeld. A Gaussian Prior for Smoothing Maximum Entropy Models.Feb. 1999.
J. Breese, et al., Empirical Analysis of Predictive Algorithms for Collaborative Filtering, in Proceedings of the 14th Conference on Uncertainty in Artificial Intelligence, 1998, pp. 43-52, AUAI, Morgan Kaufmann, San Francisco.
M. Czerwinski, et al., Visualizing Implicit Queries for Information Management and Retrieval, in Proceedings of CHI'99, ACM SIGCHI Conference on Human Factors in Computing Systems, 1999, pp. 560-567, Ass'n for Computing Machinery, Pittsburgh, PA.
S. Dumais, et al., Inductive Learning Algorithms and Representations for Text Categorization, in Proceedings of the 7th Internat'l. Conference on Information and Knowledge Mgmt., 1998, pp. 148-155, Ass'n. for Computing Machinery, ACM Press, NY.
E. Horvitz, Principles of Mixed-Initiative User Interfaces, in Proceedings of CHI'99, ACM SIGCH Conference on Human Factors in Computing Systems, 1999, pp. 159-166, Ass'n. for Computing Machinery, Pittsburgh, PA.
E. Horvitz, et al., Display of Information for Time-Critical Decision Making, in Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence, 1995, pp. 296-305, Montreal, Canada, Morgan Kaufmann, San Francisco.
E. Horvitz, et al., The Lumiere Project: Bayesian Use Modeling for Inferring the Goals and Needs of Software Users, in Proceedings of the 14th Conference on Uncertaintly in Artificial Intelligence, 1998, pp. 256-265, Morgan Kaufmann, San Francisco.
E. Horvitz, et al., Time-Dependent Utility and Action Under Uncertainty, in Proceedings of the 7th Conference on Uncertainty in Artificial Intelligence, 1991, pp. 151-158, Morgan Kaufmann, San Francisco.
E. Horvitz, et al., Time-Critical Action: Representations and Application, in Proceedings of the 13th Conference on Uncertainty in Artificial Intelligence (UAI'97), 1997, pp. 250-257, Providence, RI, Morgan Kaufmann, San Francisco.
D. Koller, et al., Toward Optimal Feature Selection, in Proceedings of the 13th Conference on Machine Learning, 1996, pp. 284-292, Morgan Kaufmann, San Francisco.
H. Lieberman, An Agent That Assist Web Browsing, in Proceedings of IJCAI-95, 1995, Montreal, Canada, Morgan Kaufmann, San Francisco.

Affiliated with

Also associated with

Rating

Exponential priors for maximum entropy models does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Exponential priors for maximum entropy models, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Exponential priors for maximum entropy models will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-3797225