Prerequisites: Basic Probability, Statistics, Linear Algebra
<br> 
<br>Course Description: 
<br>
<br>This course aims to provide an introduction to the area of probabilistic models 
<br>based on graphs, and meanwhile to offer an overall view on examining the recent 
<br>trends of using graphical models in various application domains such as machine 
<br>learning, sensor network, bioinformatics, signal/multimedia processing, and 
<br>computer vision, etc. Through the study of key models, e.g., Bayesian networks, 
<br>state space models, Markov random fields, and conditional random fields, we will 
<br>investigate and test several popular algorithms related to exact or approximate 
<br>inference, including elimination algorithm, junction tree, sum-product and max-
<br>product algorithms, loopy belief propagation, and variational methods. Students 
<br>taking the course are required to submit a final term project that emphasizes an 
<br>appropriate use of graphical model techniques on their choice of application.
<br>
<br> 
<br>Course Contents:
<br>
<br>1.      Basic probability theory and graph theory
<br>
<br>2.      Representations of graphical models
<br>
<br>3.      Learning from data
<br>
<br>4.      Methods for exact inference
<br>
<br>5.      Methods for approximate inference
<br>
<br>6.      Applications
<br>
<br> 
<br>Textbook:
<br>Daphne Koller and Nir Friedman
<br>"Probabilistic Graphical Models: Principles and Techniques"
<br>The MIT Press, 1 edition, 2009
<br>
<br>https://class.coursera.org/pgm-2012-002