研究了半监督学习的一致性学习算法及其变形.通过引入圆盘定理,证明了一致性学习算法收敛的条件;针对变形学习算法,给出了使用变形矩阵的合理性解释;最后将一致性学习算法及其变形应用于人脸识别问题,对该算法中的参数以及变形矩阵进行了实验研究,并与支持向量机方法进行了性能比较.
[1] ZHU Xiaojin. Semi-supervised learning literature survey [D]. Madison:University of Wisconsin 2008.
[2] CHAPELLE O, ZIEN A. Semi-supervised classification by low density separation [A]. Barbados 2005.
[3] ZHOU Dengyong, BOUSQUET O, THOMAS N L. Learning with local and global consistency [A]. Cambridge, MA:The MIT Press 2004.
[4] ZHOU Zhihua, ZHAN Dechuan, YANG Qiang. Semi-supervised learning with very few labeled training examples [A]. Vancouver, Canada 2007.
[5] WANG Wei, ZHOU Zhihua. On multi-view active learning and the combination with semi-supervised learning [A]. Helsinki, Finland 2008.
[6] Yin, XS, Chen, SC, Hu, EL, Zhang, DQ. Semi-supervised clustering with metric learning: An adaptive kernel method [J]. Pattern Recognition: The Journal of the Pattern Recognition Society 2010, 4(4).
[7] Lu K, Zhao JD, Cai D. An algorithm for semi-supervised learning in image retrieval [J]. Pattern Recognition: The Journal of the Pattern Recognition Society 2006, 4(4).
[8] MAHDIEH S B, SAEED B S. Kernel-based metric learning for semi-supervised clustering [J]. Neurocomputing 2010, 73(7-9).
[9] 苏育才, 姜翠波, 张跃辉. 矩阵理论 [M]. 北京:科学出版社 2006.
