Weighted maximum margin discriminant analysis with kernels

• Published in: Neurocomputing (Amsterdam) Vol. 67; pp. 357 - 362
• Main Authors: Zheng, Wenming, Zou, Cairong, Zhao, Li
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.08.2005
• Subjects: Kernel discriminant analysis; Kernel-based learning algorithms; Weighted maximum margin criterion; Kernel-based learning algorithms; Weighted maximum margin criterion; Kernel discriminant analysis
• ISSN: 0925-2312; 1872-8286
• DOI: 10.1016/j.neucom.2004.12.008

A new kernel-based learning algorithm, called kernel weighted maximum margin discriminant analysis (KWMMDA), is presented in this paper. Different from the previous discriminant analysis algorithms based on the traditional Fisher discriminant criterion, KWMMDA is derived based on a new discriminant criterion, called weighted maximum margin criterion (WMMC). The better performance of KWMMDA is demonstrated by experiments on real data set.