The Machine Learning Track is intended for students who wish to develop their knowledge of machine learning techniques and applications. Machine learning is a rapidly expanding field with many applications in diverse areas such as bioinformatics, fraud detection, intelligent systems, perception, finance, information retrieval, and other areas.
1. Overall Requirements
Students must complete a total of 30 credits:
Fulfill the 12-credit core requirement.
Students must take at least 12 credits total from Section 3 ("Required Track Courses") and 4 ("Elective Track Courses") below, including at least 6 credits from section 3 and at least 3 6000-level credits from Section 4.
Students must take at least 6 credits of technical courses at the 6000-level overall.
If the number of credits used to fulfill the above requirements is less than 30, then general elective graduate courses at 4000 level or above must be taken so that the total number of credits taken is 30. At least three of these credits must be CS Department graduate course.
Students using previous courses to fulfill core or track requirements may complete the 30 graduate credits by expanding their electives selected from (a) the list of required track courses; (b) the list of elective track courses; or (c) other graduate courses.
2. Core Requirements
For the 12-credit core requirement, students take 4 courses from the following 6:
COMS W4115 Programming Languages & Translators
COMS W4118 Operating Systems
COMS W4156 Advanced Software Engineering
CSOR W4231 Analysis of Algorithms
COMS W4701 Artificial Intelligence
CSEE W4824 Computer Architecture
3. Required Track Courses
Candidates are required to complete two (2) of the following courses*:
Course ID | Title |
COMS W4252 | Introduction to Computational Learning Theory |
COMS W4771 | Machine Learning |
COMS W4772 | Advanced Machine Learning |
Students
who have completed equivalent courses with grades of at least 3.0 may
apply those courses to satisfy these requirements and devote more
credits to pursue elective courses.
4. Elective Track Courses
Students are required to take two courses from the following list, at least one of which must be a 6000-level course. Other courses on this list may be used as general electives or to replace core or required track courses when the student has received a waiver.
Course ID | Title |
COMS W4111 | Introduction to Databases |
COMS W4252 | Introduction to Computational Learning Theory |
COMS W4705 | Intro to Natural Language Processing |
COMS W4731 | Computer Vision |
COMS W4737 | Biometrics |
COMS W4761 | Computational Genomics |
COMS W4771 | Machine Learning |
COMS W4772 | Advanced Machine Learning |
| COMS W4995 | Intro Social Networks |
COMS E6111 | Advanced Database Systems |
COMS E6253 | Advanced Topics in Computational Learning Theory |
COMS E6717 (ELEN E6717) | Information Theory |
COMS E6735 | Visual Databases |
COMS E6737 | Biometrics |
COMS E6901 | Projects in Computer Science |
Search Engine Technology | |
COMS E6998 | Network Theory |
Algorithmic Game Theory | |
| COMS E6998 | Statistical Methods for NLP |
| COMS E6998 | NLP for the Web |
| COMS E6998 | Advanced Topic in Machine Learning |
| COMS E6998 | Machine Translation |
| COMS E6998 | Machine Learning for NLP |
| COMS E6998 | Intro/Distributed Data Mining |
| COMS E6998 | Analysis of social Info. Nets |
| COMS E6998 | Algorithms/Deal/Massive Data |
| CSEE E6898 | Large-Scale Machine Learning |
| CSEE E6898 | Sparse Signal Modeling |
IEOR E6613 | Optimization I |
| IEOR E8100 | Optimization Methods in Machine
Learning
|
SIEO 4150 or STAT W4201 | Probability and Statistics/Advanced Data Analysis |
| STAT W4240 | Data Mining |
STAT G6101 | Statistical Modeling and Data Analysis I |
5. General Electives
Candidates are required to complete at least 6 additional graduate credits at, or above, the 4000 level; at least 3 of these credits must be CS, the other 3 credits may be a technical or non-technical elective approved by the track advisor. Please complete a non-tech approval form, and once it is signed, forward it to Janine Maslov or Remi Moss. At most 3 credits overall of the 30 graduate credits required for the MS degree may be non-technical.
6. Track Planning
Please visit the Directory of Classes to get the updated course listings. If you would like to see how often the courses are offered, please visit the course page on the CS Department website.
Not all courses are offered every semester, or even every year; a few courses are offered only once every two or three years or even less frequently. Among the core courses, 4115, 4118, 4701, and 4231 are normally offered every semester (fall and spring) but 4156 and 4824 are normally offered only one semester per year and which semester (fall vs. spring) may vary. Among the 4000-level track electives, only 4111 is normally offered every semester; none of the 6000-level track courses are offered every semester and some are not even offered every year. There are, however, typically one or more relevant 4995 and/or 6998 offerings each semester, and its generally possible to find a suitable 6901 project any semester. For more information, please see the SEAS Bulletin CS course-offering schedule (Please note that the course-offering schedule can change due to unforeseeable circumstances; thus, it should only be used as a reference).7. Contact
Please direct all questions concerning the Machine Learning Track to Prof. and Prof. Tony Jebara.
8. Graduation
Candidates preparing for graduation should submit a completed application for degree to the Registrar's Office and submit a track graduation form to C.S. Student Services (an example of a completed form is available here).
*Note: The list of electives may be updated to reflect changes in the schedule of course offerings.
**Please note that these course offerings are listed on a provisional basis only and may change from what is listed here.
*** ELEN-E4810 - Students who took it in Fall 06 or earlier can use it as an elective.
****IEOR E6613 - Students who took it in Fall 06 or earlier can use it as an elective.
Last updated 5/23/2012.
