CSC412S Spring 2002 - Textbook and Other Readings

Textbook

Click here to access the book.

The user name and password will be provided in class.

Readings

• Jan 7 - Ch 1 (not available), summary of Ch 4.2
• Jan 9/14 -- Ch 2.1,2.2,2.3
  
• Jan 16 -- Ch7.1.1,7.1.2,7.1.3,7.2
  Not required, but if you want some extra info on the theoretical results, I also put up Ch 15 (it uses 4.x for section numbers).
• Jan 21 -- Ch8.1,8.2, parts of Ch4.1,4.2, parts of Ch5 but not online algorithms
• Jan 23 -- Ch8.3 except 8.3.4 (IPF), parts of Ch6
• Jan18,25 -- Ch12 in tutorials
• Jan 28 -- Ch18 (not available) and these notes.
• Jan 30 -- Ch8.4,Ch9.1.0,9.1.1,9.2.0,9.2.1,9.3 (see also 4.2.1,4.2.2)
• Feb 4 -- Ch10, Ch9.1 (see also Jaakkola EM notes below)
• Feb 6/11 -- Ch13 (see also review paper below)
• Feb 13 -- Ch10, Ch9.1 (see also Neal/Hinton paper below)
• Feb 25 -- Ch4.0, Ch4.1, Ch 4.2.1
• Feb 27 -- Ch3 (see also Jaakkola elimination notes below)
• March 4/6 -- Ch11
• March 13/18/20 -- Ch16
• March 25 -- Ch17.1
• March 27 -- Ch19 (except 19.2.3)
• April 1
• April 3 -- See this page. and also this short paper.

Additional Material

• A tech report by Quaid Morris describing the construction of the QMR graphical model starting from the knowledge base.
• Notes from Tommi Jaakkola at MIT on an elimination algorithm for undirected models.
• A review paper covering Factor Analysis, PCA, the EM algorithm and some more advanced time series models.
• A paper by Neal and Hinton on the free energy view of the EM algorithm.
• Notes from Tommi Jaakkola at MIT on the EM algorithm.
• A note by Tom Minka on Graphical Models (which he calls Influence Diagrams).
• An article in AI magazine by Eugene Chaniak entitled Bayesian Networks without Tears.
• A tutorial on learning with Bayesian networks by David Heckerman.
• Berkeley class notes on fully observed trees by Mike Jordan.
• A short MATLAB tutorial.

CSC412 - Uncertainty and Learning in Artificial Intelligence || www.cs.toronto.edu/~roweis/csc412/