![](https://img-blog.csdnimg.cn/20201014180756928.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
Data mining/Machine learning
文章平均质量分 56
Calm__down
这个作者很懒,什么都没留下…
展开
-
self-training and co-training
Semi-supervised learning methods widely used include:1.EM with generative mixture models2.self-training3.co-training4.transductive support vector machines5.graph-based methodsself-training:A classifier is first traind with the small amount of labeled data.转载 2011-04-18 21:05:00 · 3536 阅读 · 0 评论 -
EM算法
EM:Expectation-maximization algorithmEM算法是机器学习中一个很重要的算法,即期望最大化算法,主要包括以下两个步骤: E步骤:estimate the expected values M步骤:re-estimate parameters可以有一些比较形象的比喻说法把这个算法讲清楚。比如说食堂的大师傅炒了一份菜,要等分成两份给两个人吃,显然没有必要拿来天平一点一点的精确的去称分量,最简单的办法是先随意的把菜分到两个碗中,然后观察是否一样多,把比较多的那一份取出转载 2011-04-18 22:09:00 · 1003 阅读 · 0 评论 -
Gaussian Mixture Model
Gaussian Mixture Model (GMM)事实上,GMM 和 k-means 很像,不过 GMM 是学习出一些概率密度函数来(所以 GMM 除了用在 clustering 上之外,还经常被用于 density estimation ),简单地说,k-means 的结果是每个数据点被 assign 到其中某一个 cluster 了,而 GMM 则给出这些数据点被 assign 到每个 cluster 的概率,又称作 soft assignment 。<br />得出一个概率有很多好处,因为它的信转载 2011-04-20 10:36:00 · 3211 阅读 · 0 评论 -
Transductive Support Vector Machine
<br />TSVM is an extension of standard support vector machines with unlabeled data. In a standard SVM only the labeled <br /> <br />data is used, and the goal is to find a maximum margin linear boundary in the Reproducing Kernel Hibert Space. In a <br /> <转载 2011-04-20 11:00:00 · 1395 阅读 · 0 评论 -
Reading Liat
David M. Blei, AndrewY. Ng, Michael I. Jordan. Latent Dirichlet Allocation, Journal of Machine Learning Research, 2003, 3: 993-1022.原创 2014-03-03 19:57:47 · 767 阅读 · 0 评论