Description of Course

Probabilistic graphical modeling and inference is a powerful modern approach to representing the combined statistics of data and models, reasoning about the world in the face of uncertainty, and learning about it from data. It cleanly separates the notions of representation, reasoning, and learning. It provides a principled framework for combining multiple sources of information, such as prior knowledge about the world, with evidence about a particular case in observed data. This course will provide a solid introduction to the methodology and associated techniques, and show how they are applied in diverse domains ranging from computer vision to computational biology to computational neuroscience.


The following textbook will be used for reading assignments. An electronic copy is available via the UA library webpage (NetID login required):

Murphy, K. "Machine Learning: A Probabilistic Perspective." MIT press, 2012 ( UA Library )

Course Management


Instructor and Contact Information:

Instructor: Jason Pacheco, GS 724, Email:
Office Hours: Fridays, 3-5pm (Zoom via D2L Calendar)
Instructor Homepage:

Date Topic Readings Assignment
1/12 Introduction + Course Overview  (slides) W3Schools : Numpy Tutorial
YouTube : Numpy Tutorial : Mr. P Solver
1/17 No Class: MLK Day
1/19 Probability Primer (Fundumentals and Discrete Probability)  (slides) CH 2.1 - 2.4 HW1 (Due: 1/26)
1/24 Probability Primer (Continuous Probability)  (slides) CH 2.4-2.7
1/26 Probability Primer (Bayesian Probability, Inference) CH 3 HW2 (Due: 2/2)
1/31 Directed Probabilistic Graphical Models CH 10.1 - 10.5
2/2 Undirected Probabilistic Graphical Models CH 19.1 - 19.4
2/7 Message Passing Inference (Variable Elimination)
2/9 Message Passing (Sum-Product Belief Propagation)
2/14 Message Passing (Loopy BP, Max-Product BP)
2/16 Message Passing (Junction Tree)
2/21 TBD
2/23 TBD
2/28 TBD
3/2 Midterm Review Midterm (Due: 3/4)
3/7 No Class: Spring Recess
3/9 No Class: Spring Recess
3/14 Dynamical Systems (HMM, Forward-Backward Algorithm)
3/16 Dynamical Systems (Linear Dynamical Systems, Kalman Filter)
3/21 Dynamical Systems (Nonlinear and Switching State-Space)
3/23 Monte Carlo Methods (Rejection Sampling, Importance Sampling)
3/28 Monte Carlo Methods (Sequential Monte Carlo)
3/30 Markov Chain Monte Carlo (Metropolis-Hastings)
4/4 Markov Chain Monte Carlo (Gibbs Sampling)
4/6 Exponential Families
4/11 Variational Inference
4/13 Variational Inference (Mean Field)
4/18 Variational Inference (Stochastic Variational)
4/20 Variational Autoencoder
4/25 TBD
4/27 TBD
5/2 TBD
5/4 Course Wrapup

© Jason Pacheco, 2020