Foundations of Machine Learning

Taught by Emtiyaz Khan, AIP-RIKEN and OIST
E-mail at
TA: Thomas Burns, and David Pere Tomas Cuesta
Goals Lecture-Notes Project-Info


Lecture Notes

Introduction to Machine Learning Slides Slides with Answers
Course Information Slides Annotated Slides
Linear Algebra (Handout) Slides
Week 1-6 (Linear Regression, SGD, Least-Squares, Ridge Regression, Cross-Validation, Bias-Variance decomposition) Notes Annotated
Week 7-8 (Classification, Logistic Regression, k-NN, DNNs) Notes

Course Goals

Evaluation is based on the following methods:
  • [40%] Class summary: Students will summarize every two weeks of lecture in their own words (a total of 5 such reports). This needs to be a summary based on understanding and can be as short as 2 pages.
  • [40%] Project report and presentation: students will submit a final project report in Week 13, and present their work in Week 14. The grading will be based on constructive feedback from the class on the project and presentation.
  • [20%] Class discussions

Students successfully completing this course will be able to:
  • Explain a few methods for Regression and Classification.
  • Implement and apply these methods to real data.
  • Discuss fundamental principles of machine learning.
  • Create an assessment of current skill level, and devise a plan for ongoing learning.

Project Information

Every (registered) student is supposed to complete a project, either alone or with another student in a team of two. Grading will be based on the constructive feedback from the class on the project report and presentation.

The main goal of the project is for students to get hands-on experiences on some of the concepts taught in the course. Students are advised to pick a project in consultation with the teaching team. Our hope is that the project will not only teach you but also give you a taste of how it is like to work on ML research projects, and how the submission and review process on conferences like NeurIPS/ICML/ICLR works.

One strategy could be to first think about a concept and topic that you might want to learn about, and choose a project that can be realistically finished in 2 months time. Our recommendation is to not choose too ambitious project, rather some simple and realistic. Remember that it takes (almost always) much more time than what we often anticipate. So one should leave enough room for uncertainties that may arise during the execution of the project.

The 4-page final project report (with supplementary and code) is due on Aug 12, 5pm JST.

To avoid last-minute rush to the deadline, we recommend students to follow the following rough schedule,

  • [June 17] Submit the team information, a potential title and abstract of the project (format to be provided later). After this date, you can still change the title/abstract, but not the team.
  • [July 1] Submit 1 page report with a title, abstract, and a plan. After this date, you can not change the project.
  • [July 15] Refine the plan (resubmit the 1-page report with a refined plan).
  • [Aug 12] Submit 4-page final project report, a supplementary (no page limit), and all the code. You will be graded only on the report, but we may look at the other material whenever necessary.
  • [Aug 16/17] Project presentation (will decide the exact duration based on the number of projects).