在统计计算中，最大期望（EM）算法是在概率（probabilistic）模型中寻找参数最大似然估计或者最大后验估计的算法，其中概率模型依赖于无法观测的隐藏变量（Latent Variable）。最大期望经常用在机器学习和计算机视觉的数据聚类（Data Clustering）领域。(In statistical calculation, the expectation maximization (EM) algorithm in probability (probabilistic) maximum likelihood estimation and maximum a posteriori estimation algorithm for parameters in the model, the probability model depends on unobservable latent variable (Latent Variable). Maximum expectations are often used in machine learning and computer vision for data clustering (Data, Clustering) fields.)