프로젝트
GitHub에서 보기
yandexdataschool/Practical_DL
yandexdataschool/Practical_DL has 1,789 GitHub stars and 658 forks. GitHot measured -2 stars in 24 hours, +1 in 7 days, and +8 in 15 days. Last checked 2026-11-20 07:51 UTC. Last push 2026-11-13.
측정된 스타 증가
- in 24h
- -2
- in 7 days
- +1
- in 15 days
- +8
- in 1 month
- 업데이트 지연
서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.
소개
DL course co-developed by YSDA, HSE and Skoltech
머신러닝README.md
OriginalDeep learning course
This repo supplements Deep Learning course taught @fall'26. For previous iteration visit the 2025 branch.
Lecture and practice materials for each week are in ./week* folders. You can complete all asignments locally or in google colab (see readme files in week*)
General info
- Telegram chat room (russian-speaking HSE track).
- Deadlines & grading rules can be found at this page.
- Any technical issues, ideas, bugs in course materials, contribution ideas - add an issue or ask around in the chat.
Syllabus
week01 Intro to deep learning
- Lecture: Deep learning -- introduction, backpropagation algorithm, adaptive optimization methods
- Seminar: Neural networks in numpy
- Homework 1 is out!
- Please begin worrying about installing pytorch. You will need it next week!
week02 Catch-all lecture about deep learning tricks
- Lecture: Deep learning as a language, dropout, batch/layer normalization, other tricks, deep learning frameworks
- Homework 2 is out!
- Seminar: PyTorch basics
week03 Convolutional neural networks
- Lecture: Computer vision tasks, Convolution and Pooling layers, ConvNet architectures, Data Augmentation
- Seminar: Training your first ConvNet
(to be updated)
Contributors & course staff
Course materials by
- Victor Lempitsky - main track lecture videos (1-11)
- Victor Yurchenko - intro notebooks, admin stuff
- Vadim Lebedev - notebooks, admin stuff
- Dmitry Ulyanov - notebooks on generative models & autoencoders
- Fedor Ratnikov - pytorch & nlp notebooks, one bonus lecture
- Oleg Vasilev - notebooks, technical issue resolution
- Arseniy Ashukha - image captioning materials
- Mikhail Khalman - variational autoencoder materials
- many bugs were fixed and course materials were improved by students and volunteers, see PR authorship