Advanced Machine Learning
Org Info and Grading
Alex Avdiushenko, Spring 2026
Course annotation
A comprehensive and cutting-edge course designed for students and practitioners
aiming to deepen their understanding of the latest advancements in the field.
This course explores a variety of advanced topics, including unsupervised learning,
the Expectation-Maximization (EM) algorithm, and the exciting world of
Large Language Models (LLMs).
Additionally, the course delves into the realms of Reinforcement Learning,
and addresses the potential of
Generative Adversarial Networks (GANs) and Diffusion models.
Practical coursework, including programming assignments
and hands-on projects, will be primarily based on Python and PyTorch.
Flipped format with live discussions of course materials, interesting challenges, and testing your understanding of machine learning
Schedule
On Tuesday, 9:00 — 12:00. Course starts on February 3
Links
Prerequisites
We invite 2+ year students with knowledge of higher mathematics and the fundamentals of machine learning.
Assignments
| No. | Topic | Start | Finish | Est. Time |
|---|---|---|---|---|
| 1 | Unsupervised Learning | Feb 3 | Feb 16 | 20 h |
| 2 | AlphaZero From Scratch | Feb 17 | Mar 9 | 30 h |
Midterm
| No. | One of | Start | Finish | Est. Time |
|---|---|---|---|---|
| 3 | Agents 101 EM and Neural networks (theory) |
Mar 10 | Mar 23 | 20 h |
| 4 | Build your Own Jarvis | Mar 24 | Apr 20 | 20 h |
Exam
The final exam will take the form of the blogpost on the internet.
Formula of the final score is the following:
FS = (Midterm)*20% + (Course work)*30% + (Blogpost)*50%