Machine learning methods are commonly used across engineering and sciences, from computer systems to physics. Moreover, commercial sites such as search engines, recommender systems (e.g., Netflix, Amazon), advertisers, and financial institutions employ machine learning algorithms for content recommendation, predicting customer behavior, compliance, or risk. As a discipline, machine learning tries to design and understand computer programs that learn from experience for the purpose of prediction or control. In this course, you will learn about principles and algorithms for turning training data into effective automated predictions. We will cover concepts such as representation, over-fitting, regularization, and generalization; topics such as clustering, classification, recommender problems, probabilistic modeling, reinforcement learning; and methods such as on-line algorithms, support vector machines, neural networks/deep learning, hidden Markov models, and Bayesian networks.

Teaching staff (6036-staff@lists.csail.mit.edu): (please read this page carefully before contacting the staff)

• Instructors: Regina Barzilay, Tommi Jaakkola, Suvrit Sra
• TAs: Polina Binder, Benjamin Greenberg, David Harwath, Nicholas Hynes, Esther Jang, Dongyoung Kim, Thanard Kurutach, Jonas Mueller, David Reshef, Tony Tran, Amruth Venkatraman, Angel Yu, Haoyang Zeng

Lectures: (tentative schedule)

• Tuesdays and Thursdays, 2:30pm–4pm (26-100)
• Regina Barzilay, Tommi Jaakkola, Suvrit Sra
• Lecture notes will be distributed within 1 week from each lecture.

Recitations:

• Weekly recitations/tutorials on Fridays
  F11-12 (32-141), F12-1 (1-190), F1-2 (35-225), F2-3 (32-141), F3-4 (4-270), F4-5 (4-163)

Exams (60% of grade):

1. Midterm on March 17, closed book, 1.5h, in-class, 20% of grade. If you have a conflict with the exam time, please notify us of your midterm conflict at least two weeks before the exam. The conflict exam (with permission only) will be the next day (Friday, March 18). In exceptional cases, the weight of the midterm can be shited to the final exam.

2. Final exam during finals week (time tbd), closed book, 3h, 40% of grade. Any conflicts with the final exam time are handled by the registrar's office.

Assignments (40% of grade in total, schedule):

1. 5 regular homework assignments (10% of the grade in total).

2. Three projects, each worth 10% of the grade, involving programming in python/MATLAB.

   • Late submission policy for homeworks and projects:

     Assignments are due 9am on specified Fridays. Solutions will be posted immediately after the deadline. Late assignments are NOT accepted. If you have a valid reason (= dean's note), you must notify us via email. For students with a valid reason in this sense, the portion of the grade allocated to the missed assignment will be added to the final exam weight. Missed assignment without a valid reason means getting the score zero on the assignment.

   • Collaboration policy for homeworks and projects:

     We encourage students to discuss assignments with other students and with the teaching staff to better understand the concepts. However, when you submit an assignment under your name, we assume that you are certifying that the details are entirely your own work and that you played at least a substantial role in the conception stage.

     You should not use results (solutions, code) from other students (from this year or previous years) in preparing yours to any assignment unless you developed the materials while working with other studens in class. Students should never share solutions (or staff solutions) with other students.