Skip to main content

Class Logistics

Course Overview​

As data and computational resources become ever more abundant, the ability to leverage both to gain insights take on an increasingly important role in our civilization. “Machine Learning” is an umbrella term for the algorithms, tools and approaches that promise to harness data in such a way. This class is a survey course intended to give an overview of all major flavors of Machine Learning. Importantly, we will place a particular emphasis on understanding the key algorithms employed in different subfields of Machine Learning, instead of treating them as a black box. Overall, the goal of this course is to enable students to become comfortable with the material to a point where they can pursue the study of more advanced topics in Machine Learning as well as employing Machine Learning methods to solve scientific and applied problems. In other words, the purpose of this class is to find out if Machine Learning is for you or not - and if it is, to enable you to pursue it further with confidence and competence.

This class is modeled on previous offerings from Spring 2022 and Fall 2021. Building on the tradition of these previous offerings, this version of the class will place a larger emphasis on practical, hands-on experience in building ML algorithms. To broaden the scope of this offering, we are also adding lectures on self-supervised learning and reinforcement learning.

Prerequisites​

A strong foundation in linear algebra, vector calculus, and introductory probability (standard probability distributions, continuous and discrete variables, expectations, and conditional expectation). Comfort with coding in Python is required.

Required

  • Data Structures (CSCI-UA.102)
  • Linear Algebra (MATH-UA.140)
  • Probability and Statistics (MATH-UA.235)

Recommended

  • CSCI-UA 310 Basic Algorithms
  • DS-GA 1001 Introduction to Data Science
    • Exercise materials are highly recommended.
  • DS-GA 1002 Statistical and Mathematical Methods

Logistical Overview​

Lecture​

  • 2:00pm-3:15pm on Tuesdays and Thursdays.
  • All lectures will be online.
  • The class will be recorded, we will post the link to the recorded lectures to the class campuswire.
  • Lectures are only accessible to enrolled students.
  • Please add the (Class calendar) to your calendar to keep track of class events (lecture, office hours, recitation, etc.).

Grading and Assignments​

  • Assignments (60%) + Capstone Project (30%) + Class Participation (10%)
  • There will be six assignments through the semester.
  • Three late days are provided for late submission. No submissions will be accepted after the late days are used by the student.

Capstone Project​

  • For the capstone project you will be asked to build a ML system for a pre-specified practical problem.
  • Project description will be released on 10/25/2022.
  • This is an individual project, and hence there will be no teams.
  • A final project report and a 1 minute video presentation of the projects is due on 12/14/2022.

Books​

The following resources will be useful but do not need to be purchased for following this class.

Other Material for Review​

Course Staff​

Office Hours​

  • Recitation slot: Mondays 8am-9:15am in CIWW 109
  • Lerrel: TBD
  • Siddhant: TBD

Remarks​

  • A student in this course is expected to act professionally. Please also follow the GSAS regulations on academic integrity found here: http://gsas.nyu.edu/page/academic.integrity
  • Academic accommodations are available for students with disabilities. Please contact the Moses Center for Students with Disabilities (212-998-4980 or mosescsd@nyu.edu) for further information. Students who are requesting academic accommodations are advised to reach out to the Moses Center as early as possible in the semester for assistance.
Last updated on