Description

Introduction to machine learning concepts, techniques, and algorithms with a focus on fairness and explainability of machine learning models. Topics include regression, classification, support vector machines, feature selection, boosting, clustering, and deep neural networks. Students will gain the intuition behind modern machine learning algorithms as well as a more formal understanding of how, why, and when they work. Course work emphasizes taking theory into practice, through applications on real-world data sets.

General Information

Prerequisites
Linear algebra (CAS CS 232 or MA 242 or equivalent)
Multivariate Calculus (e.g. CAS MA 225), including partial derivatives
Probability (CAS CS 237 or MA 381 or 581or equivalent)
Working knowledge of programming (CAS CS 111 and 112, or equivalent)
Lectures
Monday and Wednesday 12:20pm - 1:35pm in room YAW 545 (or on zoom link).

Lecture materials will be posted on the resources page.
Discussion Sections
All students should also enroll in and attend one discussion section:

CS 542 A2: Friday 8:00am - 8:50am in room EMA 304
CS 542 A3: Friday 9:05am - 9:55am in room EMA 304
CS 542 A4: Friday 10:10am - 11:00pm in room EMA 304
CS 542 A5: Friday 11:15pm - 12:05pm in room EMA 304

Discussion section materials will be posted on the resources page.
Textbooks
The recommended resources for the course are:
- Ian Goodfellow, Yoshua Bengio, Aaron Courville. Deep Learning.
- Bishop, C. M. Pattern Recognition and Machine Learning.

Other recommended supplemental textbooks on general machine learning:
- Duda, R.O., Hart, P.E. and Stork, D.G. Pattern Classification. Wiley-Interscience. 2nd Edition. 2001.
- Theodoridis, S. and Koutroumbas, K. Pattern Recognition. Edition 4. Academic Press, 2008.
- Russell, S. and Norvig, N. Artificial Intelligence: A Modern Approach. Prentice Hall Series in Artificial Intelligence. 2003.
- Hastie, T., Tibshirani, R. and Friedman, J. The Elements of Statistical Learning. Springer. 2001.
- Koller, D. and Friedman, N. Probabilistic Graphical Models. MIT Press. 2009.
Tests
Midterm exam: in-class, date TBA
Late Assignment Policy
Late programming projects and problem sets will be levied a late penalty of 0.5% per hour (up to 72 hours). After 72 hours, no credit will be given.
Collaboration/Academic Honesty
All course participants must adhere to the BU Academic Conduct Code:
http://www.bu.edu/academics/resources/academic-conduct-code/
All instances of academic misconduct must be reported to the College Academic Conduct Committee.
Grading
Participation (In-person and/or Piazza) 5%
Pre-lecture Material 10%
Problem Sets 40%
Midterm 30%
Class Challenge 15%
Scores
Scores for all students will be updated on this link as they become available: http://cs-people.bu.edu/sbargal/spring21_cs542/grades.html
You can find your scores on this page using your *random ID* that I will email you.

Announcements

Announcements are not public for this course.
Staff Office Hours
NameOffice Hours
Yiwen Gu
When?
Where?
Sarah Adel Bargal
When?
Where?
Fred Fung
When?
Where?
Kevin Delgado
When?
Where?
Yida Xin
When?
Where?
Kate Saenko
When?
Where?
Ximeng Sun
When?
Where?
Bryan A. Plummer
When?
Where?