Building support vector machines with reduced classifier...

Details Building support vector machines with reduced classifier... Building support vector machines with reduced classifier...

2006-05-10

2009-12-08

Vincent, David R (Department: 2129)

Data processing: artificial intelligence

Knowledge processing system

Reexamination Certificate

active

07630945

ABSTRACT:
Support vector machines (SVMs), though accurate, are not preferred in applications requiring great classification speed, due to the number of support vectors being large. To overcome this problem a primal system and method with the following properties has been devised: (1) it decouples the idea of basis functions from the concept of support vectors; (2) it greedily finds a set of kernel basis functions of a specified maximum size (dmax) to approximate the SVM primal cost function well; (3) it is efficient and roughly scales as O(ndmax2) where n is the number of training examples; and, (4) the number of basis functions it requires to achieve an accuracy close to the SVM accuracy is usually far less than the number of SVM support vectors.

REFERENCES:
patent: 2005/0216426 (2005-09-01), Weston et al.
Parrado-Hernandez,E. et al. “Growing support vector classifiers with controlled complexity” Pattern Recognition. vol. 36, Issue 7, pp. 1479-1488, Jul. 2003.
Fung,G. et al. “Finite Newton method for Lagrangian support vecotor machine classification” Data Mining Institute Technical Report 02-01, pp. 1-22, Feb. 2002.
Trafalis,T.B. et al. “An analytic center machine” Machine Learning vol. 46 Issue 1-3, pp. 203-223, 2002.
Milgram,J. et al. “Speeding up the decision making of support vector classifiers” IEEE Proc. of the 9th Int'l Workshop on Frontiers in Handwriting Recognition (IWFHR-9 2004), pp. 57-62, 2004.
Ali,S. et al. “Automatic parameter selection for polynomial kernel” IEEE Information Reuse and Integration, pp. 243-249, Oct. 2003.
Bi,J. et al. “Column-generation boosting methods for mixtrue of kernels” ACM KDD'04, pp. 521-526, Aug. 2004.
Diehl,C.P. et al. “SVM incremental learning, adaptation and optimization” IEEE Proc. of the Int'l Joint Conference on Neural Networks, vol. 4., pp. 2685-2690, Jul. 2003.
Guyon,I et al. “An Introduction to Variable and Feature Selection” Journal of Machine Learning Research 3: 1157-1182. 2003.
Bennett,K.P. et al. “MARK: A Boosting Algorithm for Heterogeneous Kernel Models” SIGKDD 2002.
Weston,J. et al. “Feature Selection for SVMs” 2001.
Hermes,L. et al. “Feature Selection for Support Vector Machines” IEEE. 2000.

Affiliated with

Also associated with

Rating

Building support vector machines with reduced classifier... does not yet have a rating. At this time, there are no reviews or comments for this patent.

If you have personal experience with Building support vector machines with reduced classifier..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Building support vector machines with reduced classifier... will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFUS-PAI-O-4066591