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

Subject
Prerequisites
Administrivia
Textbooks
Syllabus
Grades
Lectures

Subject

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.

Prerequisites

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 in CSE 250A are also longer and more challenging.

Administrivia

  • Professor: Lawrence Saul
  • Teaching assistants: Youngmin Cho
  • Lectures: Tue/Thu 3:30 pm - 4:50 pm, WLH 2204.
  • Sections: Mon 3:30-4:30 pm, EBU3B 4140.
  • Office hours: Fri 1:30-2:30 pm, EBU3B 3214.
  • Grading: homework (~25%), two in-class exams (~40%), final exam (~35%).

Textbooks

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:

Syllabus

Thu Sep 23 Administrivia and course overview.
Tue Sep 28 Modeling uncertainty, review of probability, explaining away. HW 1 out.
Thu Sep 30 Belief networks: from probabilities to graphs.
Tue Oct 05 Conditional independence, d-separation, polytrees. HW 1 due.
HW 2 out.
handout
Thu Oct 07 Algorithms for exact and approximate inference.
Tue Oct 12 Maximum likelihood estimation; Markov models of language; naive Bayes models of text. HW 2 due.
HW 3 out.
Thu Oct 14 Linear and logistic regression. Numerical optimization.
Tue Oct 19 Latent variable modeling. Expectation-Maximization (EM) algorithm. Auxiliary functions. HW 3 due.
Thu Oct 21 EM algorithm: derivation, proof of convergence.
Tue Oct 26 Quiz #1 HW 4 out.
Thu Oct 28 Examples of EM; applications to language modeling.
Tue Nov 02 Hidden Markov models, automatic speech recognition, Viterbi algorithm. HW 4 due.
HW 5 out.
handout
Thu Nov 04 Forward-backward algorithm, Gaussian mixture models.
Tue Nov 09 Reinforcement learning (RL), Markov decision processes. HW 5 due.
HW 6 out.
Thu Nov 11 Veterans Day: no class.
Tue Nov 16 Policy evaluation, policy improvement. HW 6 due.
Thu Nov 18 Policy iteration, value iteration.
Tue Nov 23 Quiz #2 HW 7 out.
Thu Nov 25 Thanksgiving: no class.
Tue Nov 30 Stochastic approximation theory, temporal difference prediction.
Thu Dec 02 Q-learning, extensions of RL, course wrap-up and evaluations. HW 7 due.
Mon Dec 06 Final exam.