CSE 250A. Principles of Artificial Intelligence:
Probabilistic Reasoning and Decision-Making



Probabilistic methods for reasoning and decision-making under uncertainty. Topics include: inference and learning in directed probabilistic graphical models; prediction and planning in Markov decision processes; applications to computer vision, robotics, speech recognition, natural language processing, and information retrieval.


The course is aimed broadly at advanced undergraduates and beginning graduate students in mathematics, science, and engineering. Prerequisites are elementary probability, multivariable calculus, linear algebra, and basic programming ability in some high-level language such as C, Java, or Matlab. Programming assignments are completed in the language of the student's choice.

Relation to other courses

CSE 150 covers largely the same material as CSE 250A, but at a slower pace and less advanced mathematical level. The homework assignments (and exams) in CSE 250A are longer and more challenging.


  • Professor: Lawrence Saul
  • Teaching assistant: Sheeraz Ahmad
  • Lectures: Tue/Thu 12:30 am - 1:50 pm, Peterson 102
  • Sections: Fri 1-2 pm, TM 102; Mon 5-6 pm, CSB 004.
  • Instructor office hours: Mon 3-4 pm, Fri 9-10 am.
  • TA office hours: TBD
  • Grading: homework (~25%), two in-class exams (~40%), final exam (~35%).


The course does not closely follow a particular text; the lectures are meant to be self-contained. Nevertheless, the following texts (though not required) may be useful as general references:


Thu Sep 26 Administrivia and course overview.
Tue Oct 01 Modeling uncertainty, review of probability, explaining away. HW 1 out.
Thu Oct 03 Belief networks: from probabilities to graphs.
Tue Oct 08 Conditional independence, d-separation, polytrees. HW 1 due.
HW 2 out.
Thu Oct 10 Algorithms for exact and approximate inference.
Tue Oct 15 Maximum likelihood estimation; Markov models of language; naive Bayes models of text. HW 2 due.
HW 3 out.
Thu Oct 17 Linear and logistic regression. Numerical optimization.
Tue Oct 22 Latent variable modeling. Expectation-Maximization (EM) algorithm. Auxiliary functions. HW 3 due.
Thu Oct 24 EM algorithm: derivation, proof of convergence.
Tue Oct 29 Quiz #1
HW 4 out.
Thu Oct 31 Examples of EM; applications to language modeling.
Tue Nov 05 Hidden Markov models, automatic speech recognition, Viterbi algorithm. HW 4 due.
HW 5 out.
Thu Nov 07 Forward-backward algorithm, Gaussian mixture models.
Tue Nov 12 Reinforcement learning (RL), Markov decision processes. HW 5 due.
HW 6 out.
Thu Nov 14 Policy evaluation, policy improvement.
Tue Nov 19 Policy iteration, value iteration. HW 6 due.
Thu Nov 21 Stochastic approximation theory, temporal difference prediction.
Tue Nov 26 Quiz #2 HW 7 out.
Thu Nov 28 Thanksgiving: no class.
Tue Dec 03 Q-learning, extensions of RL.
Thu Dec 05 Course wrap-up, grab-bag Q/A, evaluations. HW 7 due.
Fri Dec 13 Final exam.