Lecture 14 - Expectation-Maximization Algorithms | Stanford CS229: Machine Learning (Autumn 2018)

For more information about Stanford’s Artificial Intelligence professional and graduate programs, visit: https://stanford.io/ai Andrew Ng Adjunct Professor of Computer Science https://www.andrewng.org/ To follow along with the course schedule and syllabus, visit: http://cs229.stanford.edu/syllabus-autumn2018.html 0:00 Introduction 1:15 Unsupervised learning 1:38 First unsupervised learning algorithm 1:54 Market Segmentation 5:33 Clustering algorithm 5:37 K-means clustering 5:52 Initialize the cluster centroids 12:10 Cost function 16:32 Density Estimation 18:01 Anomaly Detection 20:40 Mixture of Gaussians Volatile 29:27 Maximum Likelihood Estimates 31:44 Bayes Rule 48:12 Jensen's Inequality 57:57 Density Estimation Problem 59:32 Maximum Likelihood Estimation 1:07:16 Concave form of Jensen's Inequality