CSE 250A. Principles of Artificial Intelligence:
Probabilistic Reasoning and Learning

 Fall 2012



Important acknowledgement: This web page, along with most other course materials, is adapted from the original created by Prof. Lawrence Saul.
  • Professor: Charles Elkan
  • Teaching assistants: Bryan Lunt, Aditya Menon, and Phuc Nguyen
  • Lectures: Tu/Th 11am to 12:20pm, Warren Lecture Hall (WLH) room 2111.
  • Two sections: 
    • Fridays from 2pm to 2:50pm in WLH 2207
    • Mondays from 1pm to 1:50pm in WLH 2205.
  • TA office hours, all in room B240A in the basement of the CSE building: 
    • Bryan Lunt: Fridays noon to 1pm
    • Aditya Menon: Wednesdays 11am to noon
    • Phuc Nguyen: Tuesdays 3pm to 4pm.
  • Grading: homework assignments (40%), in-class quizzes (20%), final exam (40%). Scores on assignments are visible on gradesource.com.

There will be a quiz in class every Tuesday starting on October 9, 2012. The last two quizzes will be on Thursdays, on November 29 and December 6. In total there will be 9 quizzes. The lowest quiz grade will be discarded, so one quiz may be missed without penalty.

There will be eight homework assignments. The first six will be handed out on Thursdays, starting on October 4, and due back at the start of lecture the following Thursday. Quizzes and assignments will both be done in pairs; please pay attention to detailed instructions.

Please ask questions using Piazza.


Methods based on probability theory for reasoning and learning under uncertainty. Topics will include directed and undirected probabilistic graphical models, exact and approximate inference, latent variables, expectation-maximization, hidden Markov models, Markov decision processes, applications to vision, robotics, speech, and/or text.


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

Relation to other courses

CSE 150 covers some of the same material as 250A, but at a slower pace and less advanced mathematical level. The homework assignments in CSE 250A are longer and more challenging. CSE 250B is at the same level as 250A, but has different content and style. Students may take either or both of 250A and 250B, in any order.


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


Lecture notes will be linked to the table below, as PDF files. The notes for one day may be in the PDF file for an earlier day.

October 2
Overview of the course, intro to Bayesian networks

October 4
Laws of probability theory, Bayesian network for the earthquake scenario
First homework assignment distributed

October 8 section notes
October 9
Simpson's paradox, explaining away, formal definition of a Bayesian network
Quiz 1
October 11
Conditional probability tables, logistic regression, d-separation
Second homework assignment distributed

October 15 section notes
October 16
Independence as absence of information flow, examples of d-separation
Quiz 2
October 18
Algorithm for computing p(X|E) in polytree networks
Third homework assignment distributed

October 22 section notes coming soon
October 23
Merging nodes and cutset conditioning for inference in loopy networks
Quiz 3

October 24 section notes on inference via stochastic sampling
October 25
Principle of maximum likelihood (ML). ML learning of parameters for a Bayesian network.
Fourth assignment

October 26 section notes
October 30
Markov models of sentences, linear regression viewed as a Bayesian network.
Quiz 4
November 1
Expectation-maximization (EM)
Fifth assignment
November 6
EM for Bayesian networks. Context-based language model.
Quiz 5
November 8
21st century data analysis and the election. EM for context-based language models and for mixture models.
Sixth assignment

Section notes on EM and mixture models for Friday November 9 and Monday November 12
November 13
Hidden Markov models (HMMs).
Quiz 6
November 15
Forward algorithm and Viterbi algorithm.
Seventh assignment, due on November 27

Section notes on HMM algorithms for Nov. 16
November 20
EM training of HMMs. Linear dynamical systems.
Quiz 7
November 22
Thanksgiving: No class.
November 27
Reinforcement learning (RL).
Last assignment, due on December 6
November 29
Policy iteration, restricted linear value functions.
Quiz 8

Section notes on MDPs and RL for Nov. 30
December 4
Approximate policy evaluation.

December 6
Least-squares policy iteration.
Quiz 9
December 12
Wednesday from 11:30am to 2:30pm: Final exam.