Machine Learning 4771 - - Home Page



**Internal**

* Home

* Handouts

* News

* Staff

* Solutions

* Tutorials

**External**

* ML People








Course Information September, 2014

Day & Time and Location

T Th 1:10pm-2:25pm at 301 Pupin

Instructor

Prof. Tony Jebara

Office Hours

T Th 2:30pm-3:15pm at 605 CEPSR

Prerequisites: Background in linear algebra and statistics*.

Description: This course introduces topics in machine learning for both generative and discriminative estimation. Material will include least squares methods, Gaussian distributions, linear classification, linear regression, maximum likelihood, exponential family distributions, Bayesian networks, Bayesian inference, mixture models, the EM algorithm, graphical models, hidden Markov models, support vector machines, and kernel methods. Students are expected to implement several algorithms in Matlab and have some background in linear algebra and statistics.

Click on "Handouts" for more details.


Bulletin Board: Courseworks (Click on Discussion)

Online Text Book: Introduction to Graphical Models The book is available via courseworks. Please login using your CUNI email address (for example ab1234@columbia.edu) and your email password. Registered students only.

Academic Honesty Policy: Please read the policy here. By staying registered in the class you indicate your acceptance of all its terms. We do not accept late homework or absence without official reasons (medical, etc.) approved by a student dean. If you miss class, please coordinate with colleagues to find out what you missed (do not email the professor to help you catch up). Once a particular grade is posted for you on Courseworks for any homework or midterm, you have two weeks to contest it. Afterwards, these grades cannot be changed (do not wait until the end of the semester to contest any grading issues that are more than two weeks old). This course assumes you have the ability to upload your work via courseworks and can figure out how to attach files. If you are incapable of using courseworks, unable to program, or unable to follow mathematical notation, please drop the class. There is a lot of math in this class, so if you do not like math, please drop the class. Finally, please take note of my office hours and come to me with your questions then (I have other commitments right after the lecture ends). If you find any of these terms unacceptable, please drop the class.

*To brush up on pre-requisites, we suggest the following books:
Strang, "Introduction to Linear Algebra," 4th edition
DeGroot and Schervish, "Probability and Statistics," 3rd edition
Feller, "Introduction to Probability," Volume 1