CSE561 - Probabilitistic Graphical Models
Teaching AssistantsAshutosh Vaish
This course will introduce the basic concepts of probabilistic graphical models. Graphical Models are a unified framework that allow to express and manipulate complex probability distributions in a compact and efficient way. They allow to one to reach mathematically sound conclusions in presence of limited and noisy observations. Many machine learning applications are tackled by the use of these models.
CO1. Students are able to construct Bayesian and Markov network representation for a given problem.
CO2. Students will know and able to apply techniques to do exact and approximate inference in the probabilistic graphical models.
CO3. Students are able to understand how to learn parameters and structure for graphical models.
1. Quiz - 10
2. Assignment -15
3. Mid-sem - 20
4. End-sem - 10
5. Project + Paper Presentation - 30
Tuesdays : 12:00-1:30 pm
Thursdays : 10:30-12:00 pm
Office hour of Instructor : Friday (4:30-5:30 pm)
Probabilistic Graphical Models: Principles and Techniques, Daphne Koller and Nir Friedman, MIT Press, 2009