https://github.com/yandexdataschool/practical_dl

DL course co-developed by YSDA, HSE and Skoltech
https://github.com/yandexdataschool/practical_dl

course course-materials deep-learning lasagne theano

Last synced: about 1 month ago
JSON representation

DL course co-developed by YSDA, HSE and Skoltech

• Host: GitHub
• URL: https://github.com/yandexdataschool/practical_dl
• Owner: yandexdataschool
• License: mit
• Created: 2016-09-15T10:43:08.000Z (almost 9 years ago)
• Default Branch: fall24
• Last Pushed: 2024-12-26T16:39:21.000Z (6 months ago)
• Last Synced: 2025-04-11T02:51:23.834Z (2 months ago)
• Topics: course, course-materials, deep-learning, lasagne, theano
• Language: Jupyter Notebook
• Homepage:
• Size: 225 MB
• Stars: 1,623
• Watchers: 69
• Forks: 647
• Open Issues: 17
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        
# Deep learning course

This repo supplements Deep Learning course taught @fall'23. _For previous iteration visit the [spring branch](https://github.com/yandexdataschool/Practical_DL/tree/spring23)._

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]([https://t.me/+Q3s6oqGWedpmOGUy](https://t.me/+OJLD95o8lYkzZDBi)) (russian).

* Deadlines & grading rules can be found at [this page](https://github.com/yandexdataschool/Practical_DL/wiki/Homeworks-and-grading-(HSE)).

* Any technical issues, ideas, bugs in course materials, contribution ideas - add an [issue](https://github.com/yandexdataschool/practical_dl/issues) 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](https://github.com/yandexdataschool/Practical_DL/issues/6). 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](http://sites.skoltech.ru/compvision/members/vilem/) - main track lecture videos (1-11)

- [Victor Yurchenko](https://github.com/simflin) - intro notebooks, admin stuff

- [Vadim Lebedev](https://github.com/vadim-v-lebedev) - notebooks, admin stuff

- [Dmitry Ulyanov](https://github.com/DmitryUlyanov) - notebooks on generative models & autoencoders

- [Fedor Ratnikov](https://github.com/justheuristic/) - pytorch & nlp notebooks, one bonus lecture

- [Oleg Vasilev](https://github.com/Omrigan) - notebooks, technical issue resolution

- [Arseniy Ashukha](https://github.com/ars-ashuha) - image captioning materials

- [Mikhail Khalman](https://github.com/mihaha) - variational autoencoder materials

- many bugs were fixed and course materials were improved by students and volunteers, see [PR authorship](https://github.com/yandexdataschool/practical_dl/pulls?q=is%3Apr+is%3Aclosed)