CSE 150 - Winter 2013
Introduction to Artificial Intelligence:
Probabilistic Reasoning and Decision Making

Prof. Lawrence Saul

Administrivia Syllabus GradeSource CAPEs

Subject

This course will introduce students to the statistical models at the heart of modern artificial intelligence. Specific topics to be covered include: probabilistic methods for reasoning and decision-making under uncertainty; inference and learning in Bayesian networks; prediction and planning in Markov decision processes; applications to intelligent systems, speech and natural language processing, information retrieval, and robotics.

Prerequisites

This course is aimed very broadly at undergraduates in mathematics, science, and engineering. Prerequisites are elementary probability, linear algebra, and calculus, as well as basic programming ability in some high-level language such as C, Java, Matlab, R, or Python. (Programming assignments are completed in the language of the student's choice.) Students of all backgrounds are welcome.

Texts

The course will not closely follow a particular text. The following texts, though not required, may be useful as general references:

Instructors

  • Professor: Lawrence Saul (saulcs.ucsd.edu)
  • Teaching assistants:
    Matthew Der (mfdercs.ucsd.edu)
    Matthew Elkherj (melkherjeng.ucsd.edu)
    Phuc Nyguen (pxn002ucsd.edu)

Meetings

  • Lectures: Tue/Thu 2:00-3:20 pm, CSB-002.
  • Office hour: Fri 1-2 pm, EBU3B-3214.
  • Discussion sections: Fri 3-4 pm (WLH 2111), Mon 3-4 pm (Center 216).
  • Tutoring hours: Mon 4-5 pm (EBU3B-B250a), Thu 3:30-4:30 pm (EBU3B-B250a), Fri 4-5 pm (EBU3B-B240a).
  • Final exam: Thu Mar 21, 3-6 pm

Grading

  • homework (25%)
  • quizzes (40%)
  • final exam (35%)

Syllabus

Tue Jan 08Administrivia and course overview
Thu Jan 10Modeling uncertainty, review of probability.
Tue Jan 15Examples of probabilistic reasoning.HW 1 out.
Thu Jan 17Belief networks: from probabilities to graphs.
Tue Jan 22Conditional independence, d-separation.HW 1 due.
HW 2 out.
Thu Jan 22Inference in polytrees and loopy networks.
Tue Jan 29Learning, maximum likelihood estimation.HW 2 due.
HW 3 out.
Thu Jan 31Naive Bayes and Markov models.
Tue Feb 05Latent variable models, EM algorithm.HW 3 due.
Thu Feb 07Examples of EM algorithm.
Tue Feb 12Quiz #1.HW 4 out.
Thu Feb 14Hidden Markov models, speech recognition.
Tue Feb 19Viterbi and forward-backward algorithms.
Belief updating. 		HW 4 due.
HW 5 out.
Thu Feb 21Reinforcement learning.
Tue Feb 26Markov decision processes.HW 5 due.
Thu Feb 28Policy evaluation, improvement, and iteration.
Tue Mar 05Quiz #2.
Thu Mar 07Bellman optimality equation, value iteration.HW 6 out.
Tue Mar 12Temporal difference learning, Q-learning.
Thu Mar 14Course wrap-up, odds and ends.HW 6 due.
Thu Mar 21Final exam