和高斯混合模型的EM算法一样，这也是拟合Bernoulli混合模型的EM算法。GMM对于实际值数据的聚类非常有用。然而，对于二进制数据（如字包特征），Bernoulli混合更适合。
Just like EM of Gaussian Mixture Model, this is the EM algorithm for fitting Bernoulli Mixture Model. GMM is useful for clustering real value data. However, for binary data (such as bag of word feature) Bernoulli Mixture is more suitable.
资源文件列表
mixBern/demo.m , 126
mixBern/logsumexp.m , 487
mixBern/mixBernEm.m , 1196
mixBern/mixBernRnd.m , 928
license.txt , 1307