Email:
xfern@eecs.oregonstate.edu

Office:
Kelly 3073

Office Hours: MW 11-12 (before class) or by
appointment

Class email list: cs534-sp12@engr.orst.edu

TA:
Beatrice Moissinac (moissinb@onid.orst.edu)

office hours: Thur 10-12

Course information (policy, learning
objectives etc)

Quick links: Announcements, textbook and materials, assignments, lectures

- Review session has been scheduled to take place Friday
04/06 1-3pm in Kelly 1007.

*Welcome to CS534! Please check this page often for new updates.**You can check out CS534 2011 class webpage for old notes.*

- (Highly) recommended text:
*Pattern recognition and machine learning*, by Chris Bishop. 1st edition. (CB)

- Other references:
*Machine learning,*by Tom Mitchell (TM)*Pattern Classification,*by Duda, Hart and Stork. 2nd Edition (DHS)

- The following resources would be
helpful for reviewing some of the important concepts that will
be used throughout the course:

- A
brief review of basic probablity concepts I
found this material on Andrew Ng's standford ML class
webpage. By the way, Andrew's notes for his ML class are
first rate, definitely worth taking a look.

- A brief review of linear algebra and vector calculus
- Matrix Cookbook Great reference for matrix related derivations.
- Useful video lectures

- Written assignment 1 due Friday 4/13 in class (solution set).
- Programming assignment 1 due Monday
4/23 in class. Data sets:

- Regression dataset: training;
testing The
first three columns correspond to the features, and the last
column correspond to the target variable y.

- Perceptron dataset: twogaussian and iris-twoclass. For these files, the first column stores the class label, which is either +1 or -1.
- Written assignment 2 due Wed 4/25
in class (solution set)

- Final project information page
- Written assignment 3 due Wed 5/2
in class (solution set)

- Programming assignment 2, the 20newsgroup dataset, deadline extended to May 14th noon.
- Written assignment 4 due Friday
5/18 in class (solution set)

- Written assignment 5 due Friday 5/25 in class (solutoin set)
- Written assignment 6 due Wednesday
6/6 in class (solution set)

- Programming assignment 3, training, testing, due on Wed 5/30

- Week
1(4/2/12-4/6/12)

- Week
2 (4/9/12- 4/13/12)
- Bias variance
analysis,

- Linear classifier - perceptron (slides)

- Week
3 (4/16/12-4/20/12)

- Week
4 (4/23/12 - 4/27/12)
- Week
5 (4/30/12- 5/4/12)

- Week
6 (5/7/12 - 5/11/12)

- Week 7 (5/14/12 - 5/18/12)

- Week 9 (5/28/12-6/1/12)
- Expectation maximization (Andrew
Ng's Notes on EM)

- Spectral clustering (slides)

- Week 10 (6/4/12-6/8/12)
- Model selection for unsuperivsed learning (slides)

- Dimension reduction (slides)

- Final Project Presentation (6/8/12) 11AM-1PM (tentative presentation
schedule)

- Week 11 Final exam (Friday 7:30AM)