4ChengXiang Zhai .A Note on the Expectation-Maximization (EM) Algorithm[A] .10th Int'l Conf on Information and Knowledge Management (CIKM 2001)[C].2001.403-410.
5B Shahshahani,D Landgrebe.The Elect of Unlabeled Samples in Reducing the Small Sample Size Problem and Mitigrating the Hughes Pheonomenon[J].IEEE Trans on Geoscience and Remote Sensing,1994 ,32(5):1087-1095.
6T Zhang,F Oles.A Probability Analysis on the Value of Unlabeled Data for Classification Problems[A].Proc of the 17th Int'l Conf on Machine Learning(ICML 2000)[C].2000.1191-1198.
7Kamal Nigamy,Andrew Kachites Mccallumzy,Sebastian Thruny,et al.Text Classification from Labeled and Unlabeled Documents Using EM [M].Boston:Kluwer Academic Publishers,2000.
