This repo contains lectures slides, seminars notebooks and homeworks for the "Deep Learning 2" course at the Faculty of Computer Science of HSE University.

Details about the course organization can be found at the wiki page (in Russian).

1. The course provides 5 homework assignments and 1 competition.
2. Evaluation formula (arithmetic rounding):
   • Applied Mathematics and Information Science: $$S = \text{round}\left(0.25\cdot\text{Competition} + 0.75\cdot\frac{1}{5}\cdot\sum_{i=1}^{5}\text{HW}_i\right).$$
   • Computing and Data Science: $$S = \text{round}\left(\frac{1}{5}\sum_{i=1}^{5}HW_i\right).$$

1.  Essentials of GPU, Deep Learning Bottlenecks, and Benchmarking Basics
2.  On Transformers and Bitter Lesson
3.  Modern LLMs essentials
4.  Basics of Efficient LLM Training Infrastructure
5.  Segmentation and Detection
6.  Segmentation and Detection 2
7.  Diffusion models 1
8.  Diffusion models 2
9.  Diffusion models 3
10. 3D CV
11. Neural Recommender Systems
12. Graph Machine Learning
13. Deep Learning and Tabular Data

1.  Homework 1
2.  Homework 2
3.  Homework 3
4.  Homework 4
5.  Homework 5
5.  Competition

I would like to express my gratitude to Ivan Rubachev and Evgeny Sokolov for their invaluable help and support in designing this course. I am also deeply grateful to Denis Rakitin for his advices during the course. My thanks also go to all our guest lecturers and seminarians for agreeing to participate and share their expertise. A special thanks to Maxim Kodryan — his mere existence was contribution enough.

The content of lectures and assignments is distributed under the Apache 2.0 license: you can use and redistribute it for any purposes, as long as you refer to this course as the origin of the content.