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: Andrea Vattani and Shibin Parameswaran
  • Lectures: Mon/Wed 11:00 am - 12:20 pm, CSE Building, Room 2154.
  • Sections: Fri 12:00 - 12:50 pm, CogSci Building, Room 004.
  • Office hours: Wed 1-2 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

Mon Sep 28 Administrivia and course overview. HW 1 out.
Wed Sep 30 Modeling uncertainty, review of probability, explaining away.
Mon Oct 05 Belief networks: from probabilities to graphs. HW 1 due.
HW 2 out.
Wed Oct 07 Conditional independence, d-separation, polytrees. handout
Mon Oct 12 Algorithms for exact and approximate inference. HW 2 due.
HW 3 out.
Wed Oct 14 Maximum likelihood estimation; Markov models of language; naive Bayes models of text.
Mon Oct 19 Linear and logistic regression. Numerical optimization. HW 3 due.
Wed Oct 21 Latent variable modeling. Expectation-Maximization (EM) algorithm. Auxiliary functions.
Mon Oct 26 Quiz #1 HW 4 out.
Wed Oct 28 EM algorithm: derivation, proof of convergence, and examples.
Mon Nov 02 Hidden Markov models (HMMs), automatic speech recognition. HW 4 due.
HW 5 out.
Wed Nov 04 Viterbi and forward-backward algorithms in HMMs.
Mon Nov 09 Multivariate Gaussian distribution, mixture models, Kalman filtering. HW 5 due.
HW 6 out.
Wed Nov 11 Veterans Day: no class.
Mon Nov 16 Reinforcement learning (RL), Markov decision processes (MDPs). HW 6 due.
Wed Nov 18 Policy evaluation, policy improvement.
Mon Nov 23 Quiz #2
Wed Nov 25 Policy iteration, value iteration. HW 7 out.
Mon Nov 30 Stochastic approximation theory, temporal difference prediction.
Wed Dec 02 Q-learning, extensions of RL, course wrap-up and evaluations. HW 7 due.
Tue Dec 08 Final exam.