girafe-ai/ml-course

Open Machine Learning course

  • What it is: A GitHub repository that hosts the full materials for a first-semester machine learning course, created by the group girafe-ai. It is not a software library — it is a structured course site.

  • Contents: A weekly schedule (from September to November) in which each week covers a different ML topic. For each week the repository provides:

    • the topic name (e.g., Intro, Naive Bayes and kNN, Linear Regression, SVM, PCA, Trees and ensembles, Gradient boosting, Intro into Deep Learning, Backpropagation, Dropout and Batchnorm, Embeddings and seq2seq model),
    • links to recorded lectures and seminars (YouTube),
    • slide PDFs,
    • homework assignments (with deadlines) and some labs.

  • Format: A typical week consists of a lecture and a seminar. Some weeks have homework with a deadline (given as 23.59 AOE — a standard academic deadline timezone), while others are optional or have no homework. One week mentions a test/proctored work instead of a seminar; another week had the lecture cancelled but a backup seminar was held.

  • Prerequisites: The course lists its prerequisites in a separate file (prerequisites.md) inside the repository — the README does not state what they are, only that they exist.

  • Recommended literature: Three books are suggested:

    1. YSDA ML Book (Russian only),
    2. Probabilistic Machine Learning: An Introduction (with a Russian translation), and
    3. Deep Learning Book (English).

  • Exam: An exam program is available as a PDF file (approximate_program.pdf) inside the repository.

  • People:

    • Main authors: Radoslav Neychev and Vladislav Goncharenko.
    • Contributors: Iurii Efimov, Nikolay Karpachev, Ivan Provilkov, Valery Marchenkov, Anastasia Ianina, Irina Rudenko, Fedor Ryabov.
    • Acknowledgements to several individuals (including Stanislav Fedotov from YSDA, Konstantin Vorontsov, Vadim Strijov, and Just Heuristic) for discussions, program verification, and support.

  • Additional links: The README also points to a separate branch (“ML trainings of Yandex 2023”) and to extra materials (extra_materials.md), but does not describe them further.

  • Note on language: The course materials are written in a mix of Russian and English (headings, comments, and the README itself use Russian). No claim about language support is made beyond that.

No installation, usage, or code examples are mentioned in the README — this repository is purely a course material hub.

Related

  • Project
    mne-tools/mne-python

    An open-source Python package for exploring, visualizing, and analyzing human neurophysiological data like MEG and EEG.

  • Project
    facebookresearch/pytorchvideo

    PyTorchVideo is a PyTorch‑based library that supplies video‑focused data loaders, transforms, and a zoo of pretrained models (e.g., SlowFast, X3D, MViT) for research and development of video understanding AI. It streamlines training and fast inference, supports mobile deployment, and is open‑source under Apache 2.0.

  • Project
    NVIDIA/TransformerEngine

    NVIDIA Transformer Engine is an open‑source library that speeds up Transformer model training on NVIDIA GPUs by providing fused kernels and automatic mixed‑precision APIs (FP8, MXFP8, NVFP4, BF16, FP16) for PyTorch and JAX. It handles scaling‑factor management, quantization metadata, and distributed communication, letting users adopt low‑precision training without changing their code. Integrated with major LLM frameworks (Hugging Face, Lightning, Megatron‑LM, etc.), it targets large‑scale language, vision, and MoE models on Hopper/Blackwell/Rubin hardware.

  • Project
    apache/singa

    Apache SINGA is a distributed deep learning system that enables the training of large-scale neural networks across multiple machines.