The Machine Learning Track

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.


Machine Learning track students must complete a total of 30 points and must maintain at least 2.7 overall GPA in order to be eligible for the MS degree in Computer Science.

  1. Machine Learning track requires:- Breadth courses
    – Required Track courses (6pts)
    – Track Electives (6pts)
    – General Electives (6pts)
  2. Students must take at least 6 points of technical courses at the 6000-level overall. One of the Track Electives courses has to be a 3pt 6000-level course from the Track Electives list.
  3. If the number of points 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.
  4. Students using previous courses to fulfill track requirements may complete the 30 graduate points by expanding their electives selected from (a) the list of required track courses; (b) the list of Track Elective courses; or (c) other graduate courses.

Please use the Degree Progress Checklist to keep track of your requirements.


Visit the breath requirement page for more information.


Students must complete two required track courses by either taking two courses from group A, or one course from group A plus one course from group B. (At least one course must be taken from group A). Students who have taken equivalent courses in the past and received grades of at least a B may apply for waivers and take other CS courses instead.


Course ID


A COMS W4252 Introduction to Computational Learning Theory
A COMS W4771 or COMS W4721 or ELEN 4720[1] Machine Learning OR Machine Learning for Data Science OR Machine Learning for Signals, Information and Data
A COMS W4772 or COMS 6772 Advanced Machine Learning
A COMS 4995 Neural Networks Deep Learning
A COMS/STAT G6509/6701 Foundations of Graphical Models (This course is an advanced course, but MS students may register for it with instructor approval)
A COMS 4732 Computer Vision II
A COMS 4773 Machine Learning Theory
A COMS 4774 Unsupervised Learning
A COMS 4775 Causal Inference (Previously listed as COMS 4995: Causal Inference)
B COMS W4731 Computer Vision I
B COMS W4705 Natural Language Processing
B COMS W4733 Computational Aspects of Robotics
B COMS W4701 Artificial Intelligence
[1] Due to significant overlap, students can receive credits for only one of these courses (either COMS W4771 Machine Learning or COMS W4721 Machine Learning for Data Science OR ELEN 4720 (as of Spring 2020) Machine Learning for Signals, Information and Data).


Students are required to take 2 courses from the following list, at least one of which must be a 6000-level course. Student cannot ‘double count’ a course that they took as a required track course as a track elective. Other courses on this list may be used as General Electives or to replace required track courses when the student has received a waiver.

Course ID


COMS W4111 Introduction to Databases
COMS W4252 Introduction to Computational Learning Theory
CSOR W4246 Algorithms for Data Science
COMS W4705 Intro to Natural Language Processing
COMS W4731 Computer Vision
COMS W4733 Computational Aspects of Robotics
COMS W4737 Biometrics
COMS W4761 Computational Genomics
COMS E4762 Machine Learning for Functional Genomics
COMS W4771 or COMS W4721 or ELEN 4720[1] Machine Learning OR Machine Learning for Data Science OR Machine Learning for Signals, Information and Data
COMS W4772 or COMS 6772 Advanced Machine Learning (or COMS 6998: Machine Learning Personalization only valid if taken in Spring 2018)
COMS W4776 Machine Learning for Data Science
COMS W4995 Visit the topics courses page to see which COMS 4995 courses apply to this track.
COMS E6111 Advanced Database Systems
COMS E6232 Analysis of Algorithms II
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 (Advisor approval required)
COMS E6998 Visit the topics courses page to see which COMS 6998 courses apply to this track.
CSEE E6892 Bayesian Models in Machine Learning
CSEE E6898 Large-Scale Machine Learning
CSEE E6898 Sparse Signal Modeling
APMA E4990 Modeling Social Data
BINF G4006 Translational Bioinformatics
ECBM E4040 Neural Networks and Deep Learning
ECBM E6040 Neural Networks and Deep Learning Research
EECS E6691 Topics in  Data-Driven Analysis & Comp: Advanced Deep Learning
EECS E6699 Topics in Data-Driven Analysis and Computation: Mathematics of Deep Learning
EECS E6720 Bayesian Models of Machine Learning
EECS E6870 Speech Recognition
EECS E6893 Big Data Analytics or Topics-Information Processing (May only count 1 of these)
EECS E6895 Topic Adv Big Data Analytics
EECS E6894 Deep Learning for Computer Vision and Natural Language Processing
ELEN 6885 Reinforcement Learning
ELEN E6886 Sparse Representations and Higher Dimensional Geometry
ELEN E6899 Topics in Information Processing: Autonomous Multi-Agent Systems
IEOR E6613 Optimization I
IEOR E8100 Optimization Methods in Machine Learning
IEOR E8100 Big Data & Machine Learning
IEOR E8100/4575 Reinforcement Learning
MECS E6615 Advanced Robotic Manipulation
STAT W4201/4291/5291 or IEOR 4150 Probability and Statistics/Advanced Data Analysis
STAT W4240* Data Mining
STAT W4282 Linear Regression/Time Series Analysis
STAT W4249/STAT 4243 Applied Data Science
STAT G4400/4241/5241* Statistical Machine Learning
STAT W4640/4224/5224 Bayesian Statistics
STAT 5242 Advanced Machine Learning
STAT W4700 Probability and Statistics
STAT G6101 Statistical Modeling and Data Analysis I
STAT G6104 Computational Statistics
STAT GR8101 Topics in Applied Statistics: Applied Causality
[1] Due to significant overlap, students can receive credits for only one of these courses (either COMS W4771 Machine Learning or COMS W4721 Machine Learning for Data Science OR ELEN 4720 Machine Learning for Signals, Information and Data).

*Due to a significant overlap in course material, students in the Machine Learning track can only take 1 of the following courses – ELEN 4903, IEOR 4525, STAT 4240, STAT 4400/4241/5241 – as a track elective or a general elective.

** STAT 4001 (previously known as SIEO 4150) will ONLY be accepted as a track elective if taken Spring 2018 or prior.


Students are required to complete at least 6 additional graduate points at, or above, the 4000 level; at least 3 of these points must be CS, the other 3 points may be non-CS/non-track course approved by the track advisor. Candidates who wish to take a non-CS/non-track course should complete a non-track approval form, get the advisor’s approval, and submit it to CS Student Services. At most 3 points overall of the 30 graduate points required for the MS degree may be non-CS/non-track.


Please visit the Directory of Classes to get the updated course listings. Please also note that 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.

Please note that some Data Science Institute courses such as COMS W4121 (Computer Systems for Data Science) do not count towards the CS MS degree. If you have any questions, please contact your advisor or the CS Student Services.

As of Spring 15, STAT W4252 Introduction to Data Science is no longer an approved track elective course.

** Known Non-Track Course**

CSOR E4995 Financial Software Systems


Please check your MICE profile for your track advisor assignment. All questions regarding your track can be sent directly to your assigned faculty advisor.


Candidates preparing for graduation should submit a completed application for degree to the Registrar’s Office and submit a track graduation form/checklist to CS Student Services.

Last updated 1/22/2019.