Instructor: Aaron Bobick Office: CCB 316 afb@cc.gatech.edu Office Hours: Tues 2-3pm (but better to make email appointment because of travel)

TA:Abhijit Kundu Office: CCB 304L abhijit.dgp@gmail.com Office Hours: Fri 4-5pm

TA: Shray Bansal Office: CCB308 shray.bansal@gmail.com    Office Hours:  Fri 3-4pm

 

 

 

 

 

 

********************************************************************************************

ALERTS for REGISTRATION:

Jan 3:  The course is over subscribed.  Just come to class and we’ll work it out.   

Jan 7:  Wow.  85 people class.  40 signed the overload request form.  I am guessing only 10 of the original 30 will drop.  So that’s 60 who want credit.  We are definitely changing rooms.  But I don’t know yet how many overloads will be processed.  Priority will likely be given to CoC grad students. 

Jan 7:  We may need another student to be paid as a grader.  If you’re interested please send me (afb@cc.gatech.edu) email.

Jan 8:  NEW CLASSROOM!!!  Class has been moved to Klaus 1443.  It holds 200.  We should be safe!

********************************************************************************************

Who is this for?  This is a graduate level for those interested in pattern recognition in general and for some elements as applied to computer vision.  It is *not* going to be a comprehensive Machine Learning course. 

Prerequsites:   Since this is a graduate course we are typically quite loose with prerequisites.  Recommendations: 

·         A good foundation of probability and linear algebra.  This class will have more math in it than most Computer Science classes.

·         Any Machine Learning background will help.  Though the course won’t technically presume ML as a background it will be much easier to grasp if you’ve seen things like graphical models or other inference structures. 

·         A good working knowledge of Matlab or Python with Numpy.   We will likely be doing things in Matlab in class.  I am pretty sure that Octave will be OK though the lack of some plotting make may some figures harder to generate.  Because this is my first time offering this class I can only speculate on this.

Textbooks

This is a tough one.  The two texts that I am certain we’ll draw from are:

·       “The Elements of Statistical Learning: Data Mining, Inference, and Prediction. (2^nd Ed)”  by Hastie,  Tibshirani, and Friedman (web site, Amazon).  The book is available as a free PDF from the web site but it is also only $73 from Amazon which is relatively inexpensive for such a good text.

 

·       “Machine Learning: a Probabilistic Perspective” by Kevin Murphy.  (web site,  Amazon).  THERE IS A LEGAL PDF in the GT Library (https://portal.library.gatech.edu/vufind/Record/1195667) but this is a best-seller (well, best selling ML book on Amazon) and is also relatively inexpensive at about $75. 

I’ll also use as a crutch a more basic text:

·         “Pattern Classification” by Duda, Hart and Stork (Amazon)  This is a classic text (used to be just Duda and Hart) that I first learned PatRec in.  In some sense it mostly predated “modern” Machine Learning, but it’s extremely accessible.

We will require readings from both Hastie and Murphy.

 

Administrative

·         Web site: This site.  Will have posted calendar/syllabus with posted slides, problem sets with data, other administrative stuff.

·         T-square:  The usual stuff. There is a web page under resources that points to this class web page.

·         Slides: PDF slides will be posted by linking to the calendar.  As these will be collaborative lectures (more on that in class) they will probably not be posted before class. 

·         Piazza: You will all receive an invitation to Piazza for CS7616.  If not, send us email.  I do not yet know if this will be as useful for this class as it is for my Computer Vision class, but we’ll see. Rather than emailing questions to the teaching staff (ie me), I encourage you to post your questions on Piazza. Find our class page at: https://piazza.com/gatech/spring2014/cs7616/home

·         Matlab access:  if you don’t know how to get MATLAB access, first ask a friend. Then come see the TAs or me.   I believe Octave will be adequate.

·         Python access: some of you may use Python and Numpy.  We’ll try to give you some support but mostly you’re venturing into the great unknown.

Grading

Finalizing now. The grade will be based upon a small number of projects some of which can be done in groups no larger than two.  My intent is to have two or three projects where everyone in the class uses the same data set and a variety of algorithms, whereas for the “final” project you will need to propose your own pattern recognition problem/data set.  Also, everyone will be responsible for presenting some Pattern Recognition material, combining what is in the textbook(s) with more recent or topical work,

·         Communal Projects: 60%

·         Final project:  25%

·         Class presentation: 15%

·         Class participation: max 5%  (ie it can only raise your grade)

Late Policy

Don't be late, it’s not fair to the TA.  We will not accept late home works for full credit it unless you have (several day) prior approval from the professor for really extenuating circumstances.   Submit what you have on time. 

Honesty and Integrity Policy

Projects are to be done individually (or within your group) but you may collaborate at the white board level. You may help each other with algorithms and general computation, but your code must be your own.  REPEAT: THE CODE MUST BE YOUR OWN.  ANYTHING TAKEN FROM THE WEB IS NOT YOUR OWN!!!!

 

 

 

Last modified: 2/3/2014