The Community for Technology Leaders
RSS Icon
Subscribe
Los Angeles, CA
March 31, 2009 to April 2, 2009
ISBN: 978-0-7695-3507-4
pp: 689-693
ABSTRACT
Matrix-pattern-oriented Ho-Kashyap classifier has been demonstrated to have a superior classification performance to its vector classifier. However, it is found that the matrixized classifier takes a large computational complexity for convergence in some cases. To overcome the disadvantage, this paper introduces the early stopping technique into the matrixized Ho-Kashyap classifier and presents a Matrix-pattern-oriented Ho-Kashyap classifier with Early Stopping named MatHKES. The presented MatHKES adopts early stopping as a new regularization technique instead of adding a regularization parameter in the criterion. The proposed algorithm achieves: 1) a less running time; 2) a competitive or better classification performance; 3) an avoidance of over fitting in training.
CITATION
Songcan Chen, Zhe Wang, Xuelei Ni, "Matrix-Pattern-Oriented Ho-Kashyap Classifier with Early Stopping", CSIE, 2009, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE, 2009 WRI World Congress on Computer Science and Information Engineering, CSIE 2009, pp. 689-693, doi:10.1109/CSIE.2009.8
9 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool