Active feature probing using data augmentation

Details Active feature probing using data augmentation Active feature probing using data augmentation

2011-06-07

2011-06-07

Holmes, Michael (Department: 2129)

Data processing: artificial intelligence

Machine learning

C706S045000

Reexamination Certificate

active

07958064

ABSTRACT:
Systems and methods are disclosed that performs active feature probing using data augmentation. Active feature probing is a means of actively gathering information when the existing information is inadequate for decision making. The data augmentation technique generates factitious data which complete the existing information. Using the factitious data, the system is able to estimate the reliability of classification, and determine the most informative feature to probe, then gathers the additional information. The features are sequentially probed until the system has adequate information to make the decision.

REFERENCES:
patent: 6058205 (2000-05-01), Bahl
patent: 6557011 (2003-04-01), Sevitsky
patent: 7087018 (2006-08-01), Comaniciu et al.
patent: 7458936 (2008-12-01), Zhou et al.
patent: 7738705 (2010-06-01), Casadei
patent: 2004/0133083 (2004-07-01), Comaniciu et al.
patent: 2004/0193036 (2004-09-01), Zhou et al.
Zhu et al (“Dynamic Active Probing of Helpdesk Databases” VLDB'08, Aug. 24-30).
Zhou et al (“Conditional Feature Sensitivity: A Unifying View on Active Recognition and Feature Selection” ICCV'03) Date Unknown.
Mirzadeh et al (“Feature Selection Methods for Conversational Recommender Systems” EEE'05 Mar. 29-Apr. 1).
Yang et al (“Enhancing the Effectiveness of Interactive Case-Based Reasoning with Clustering and Decision Forests” Applied Intelligence, 2001).
Wang et al (“iHelp: An Intelligent Online Helpdesk System” IEEE 2010).
Ackley, D. R., Hinton, G. E., & Sejnowski, T. J. (1985). A learning algorithm for Boltzmann machines. Cognitive Science, 9, 147-169.
Cohn et al, Active Learning with Statistical Models, J. Artificial Intelligence Res. 4 (1996), 129-145.
Dempster, A. P., Laird, N. M., & Rubin, D. B. (1976). Maximum likelihood from incomplete data via theEM algorithm. Proceedings ofthe Royal Statistical Society, 1-38.
A. Efros, A. A., & Leung, T. K. (1999). Texture synthesis by non-parametric sampling.IEEE International Conference on Computer Vision(pp. 1033-1038). Corfu, Greece.
Franz et al, Unsupervised and Supervised Clustering for Topic Tracking, NAACL-2001.
Ghahramani, Z., & Jordan, M. L (1994). Supervised learning from incomplete data via anEM approach.Advances in Neural Information Processing Systems(pp. 120127). MorganKaufmann Publishers. Inc.
Heckerman, A tutorial on learning Bayesian networks, Technical Report MSR-TR-9506 (Mar. 1995).
Seung et al, Query by Committee, date unknown.
Xu et al., Query Expansion Using Local and Global Document Analysis, date unknown.
Kumaran et al., Simple Questions to Improve Pseudo-Relevance Feedback Results, SIGIR'06, Aug. 6-10, 2006, Seattle, WA.

Affiliated with

Also associated with

Rating

Active feature probing using data augmentation does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Active feature probing using data augmentation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Active feature probing using data augmentation will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-2637892