Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/girafe-ai/ml-course
Open Machine Learning course
https://github.com/girafe-ai/ml-course
computer-vision course deep-learning machine-learning materials natural-language-processing python pytorch reinforcement-learning seminars
Last synced: 25 days ago
JSON representation
Open Machine Learning course
- Host: GitHub
- URL: https://github.com/girafe-ai/ml-course
- Owner: girafe-ai
- License: mit
- Created: 2019-02-01T16:20:39.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2024-05-29T00:16:51.000Z (5 months ago)
- Last Synced: 2024-06-13T11:20:13.694Z (5 months ago)
- Topics: computer-vision, course, deep-learning, machine-learning, materials, natural-language-processing, python, pytorch, reinforcement-learning, seminars
- Language: Jupyter Notebook
- Homepage:
- Size: 680 MB
- Stars: 2,071
- Watchers: 66
- Forks: 1,051
- Open Issues: 35
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- AiTreasureBox - girafe-ai/ml-course - 11-02_2288_1](https://img.shields.io/github/stars/girafe-ai/ml-course.svg)|Open Machine Learning course| (Repos)
README
[**Ссылка на ветку ML тренировок Яндекса 2023**](https://github.com/girafe-ai/ml-course/tree/23f_yandex_ml_trainings)
# Machine Learning course
First semester of girafe-ai Machine Learning course## Recordings and materials
| Date | Content | Lecture video | Slides | WarmUp test | HW | Deadline | Comments |
|:------:|:-----------------------|:------------:|:------------:|:-----------------------:|:------------------------:|:----------------------:|:----------------------:|
| 05.09.2022 | Week01. Intro, Naive Bayes and kNN. | [Запись лекции 2021](https://youtu.be/74Kd-rNxSm0) [Запись семинара 2021](https://youtu.be/bzCwHkO-YEk)| [Слайды](week0_01_naive_bayes/lect001_intro_knn_naive_bayes.pdf) | | [Assignment 01: kNN](homeworks/assignment0_01_knn) | 23.59 AOE, 03.10.2022 | *По техническим причинам запись лекции 2022 года не велась*
| 12.09.2022 | extra Week. Linear algebra recap. | [Запись лекции](https://youtu.be/vKfdtHnXVEY?list=PLJR10EXrBaAv2vPy05qesewHv9JFc8ZjM) [Запись семинара 2022](https://youtu.be/Ha3pJJnt5YA?list=PLJR10EXrBaAv2vPy05qesewHv9JFc8ZjM)| [Слайды](week0_00_linear_algebra_recap/lecture00-linear_algebra_recap.pdf) | | | | |
| 19.09.2022 | Week02. Linear Regression. | [Запись лекции](https://youtu.be/imzlM4jRbD4?list=PLJR10EXrBaAv2vPy05qesewHv9JFc8ZjM) [Запись семинара 2022](https://youtu.be/LLGLeM3JKDQ?list=PLJR10EXrBaAv2vPy05qesewHv9JFc8ZjM) | [Слайды](week0_02_linear_reg/lect002_linear_regression.pdf) | | [Assignment 02: Linear Regression](homeworks/assignment0_02_lin_reg) | 23.59 AOE, 10.10.2022 | |
| 26.09.2022 | Week03. Linear Classification. | [Запись лекции](https://youtu.be/db1XU_WJHFs?list=PLJR10EXrBaAv2vPy05qesewHv9JFc8ZjM) [Запись семинара 2022](https://youtu.be/vSeETg1two8) | [Слайды](week0_03_linear_classification/msai-ml_s21_lect003_logistic_regression.pdf) | | [Lab01: ML pipeline](https://github.com/girafe-ai/ml-course/tree/22f_basic/homeworks/lab01_ml_pipeline) | 23.59 AOE 10.11.2022 |
| 03.10.2022 | Week04. SVM, PCA. | [Запись лекции](https://youtu.be/mlA-XxC9Ugg?list=PLJR10EXrBaAv2vPy05qesewHv9JFc8ZjM) [Запись семинара 2022](https://youtu.be/z-JqKoyHHRI?list=PLJR10EXrBaAv2vPy05qesewHv9JFc8ZjM) | [Слайды](week0_04_svm_and_pca/lect004_svm_pca.pdf) | | [Assignment 03: SVM kernel](https://github.com/girafe-ai/ml-course/tree/22f_basic/homeworks/assignment0_03_svm) | 23.59 AOE, 24.10.2022 |
| 10.10.2022 | Week05. Trees and ensembles | [Запись лекции](https://youtu.be/kbNZsQj2eHk) | [Слайды](week0_05_trees_and_ensembles/lect005_trees_and_ensembles_style.pdf) | | [Optional assignment 04: Tree from scratch](https://github.com/girafe-ai/ml-course/tree/22f_basic/homeworks/assignment0_04_tree) | 23.59 AOE, 22.12.2022 | Вместо семинара проходила контрольная работа |
| 17.10.2022 | Week06. Gradient boosting | [Запись лекции](https://youtu.be/Y97xrRiLY1Q) [Запись семинара](https://youtu.be/4vo39B6M270) | [Слайды](week0_06_boosting/week0_06_gradient_boosting.pdf) | | | | |
| 24.10.2022 | Week07. Разбор теста | [Запись разбора](https://youtu.be/YiO1N6yVJcg) | | | | | Вместо лекции были тест и разбор. |
| 31.10.2022 | Week08. Intro into Deep Learning | [Запись лекции](https://youtu.be/G--msc2IR-Y) [Запись семинара](https://youtu.be/0WMAfRuFHy8) | [Слайды](https://github.com/girafe-ai/ml-course/blob/22f_basic/week0_07_intro_to_DL/lect007_intro_to_dl_style.pdf) | | | | |
| 07.11.2022 | Week09. Backpropogation | [Запись семинара](https://youtu.be/HGk5xQ0azdo) | [Слайды]() | | | | Лекция не велась по причине болезни преподавателя, однако был проведён дополнительный семинар по backpropogation |
| 14.11.2022 | Week10. Dropout and Batchnorm | [Запись лекции](https://youtu.be/UtEV_ILJTA0) [Запись семинара](https://youtu.be/tq-mmdsW5QI) | [Слайды](https://github.com/girafe-ai/ml-course/blob/22f_basic/week0_08_dropout_batchnorm/lect008_deeplearning_part_2_style.pdf) | | | | |
| 21.11.2022 | Week11. Embeddings and seq2seq model | [Запись лекции](https://youtu.be/kUAnB_Leg6E) [Запись семинара](https://youtu.be/KOIEozoCQo0) | [Слайды](https://github.com/girafe-ai/ml-course/blob/22f_basic/week0_09_embeddings_and_seq2seq/lect009_Language_models_and_RNN.pdf) | | | | |## Prerequisites
Prerequisites are located [here](./prerequisites.md).## Literature:
1. [YSDA ML Book](https://academy.yandex.ru/dataschool/book) (Russian only)
2. Probabilistic Machine Learning: An Introduction; [English link](https://probml.github.io/pml-book/book1.html), [Русский перевод](https://dmkpress.com/catalog/computer/data/978-5-93700-119-1/)
3. Deep Learning Book: [English link](https://www.deeplearningbook.org/). Первая часть (Part I) крайне рекомендуется к прочтению.
More additional materials are available [here](https://github.com/girafe-ai/ml-course/blob/22f_basic/extra_materials.md)## Exam program:
Available [here](./approximate_program.pdf)## Main authors:
* Radoslav Neychev
* Vladislav Goncharenko## Contributors:
* Iurii Efimov
* Nikolay Karpachev
* Ivan Provilkov
* Valery Marchenkov
* Anastasia Ianina
* Irina Rudenko
* Fedor Ryabov## Acknowledgements:
Special thanks to:
* Stanislav Fedotov, YSDA for informative discussions, program verification and support.
* Konstantiv Vorontsov
* Vadim Strijov for teaching this course teachers
* Just Heuristic