# yandexdataschool/Practical_DL

DL course co-developed by YSDA, HSE and Skoltech

Repository: https://github.com/yandexdataschool/Practical_DL
Canonical: https://ross.abutalabs.com/products/practical_dl
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: deep-learning, course, course-materials, theano, lasagne
Last push: 2025-12-12T20:40:11+00:00

## Health v2 (maintenance only)
Score: 57/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 56, release rhythm 35, longevity 100
- inputs: {"age_days": 3639, "days_push": 264, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1756, forks 653 (observed 2026-08-28T04:05:32.201545+00:00)

## What it is
A deep learning course repository co-developed by YSDA, HSE and Skoltech, containing weekly lecture notes, seminar notebooks, and homework assignments. Materials are Jupyter notebooks runnable locally or in Google Colab, covering topics from backpropagation to CNNs and generative models.

## Use cases
- learn deep learning from scratch
- practice building neural networks in numpy and pytorch
- find course materials for convolutional neural networks
- complete homework assignments on backpropagation and optimization
- study generative models and autoencoders
- self-study a university-level deep learning course

## When to choose
- you want structured weekly course materials with hands-on notebooks
- you prefer learning via Colab without local setup
- you want free MIT-licensed university course content

## When to avoid
- you need production deep learning tooling rather than educational materials
- you want a maintained library with API stability guarantees
- you need materials in a language other than English/Russian

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, machine-learning, developer-tools
- domain: deep-learning, machine-learning, tutorials, education
- platform: python, cross-platform
- tags: jupyter-notebooks, pytorch, course-materials, seminars, homework

## Member repositories
- yandexdataschool/Practical_DL (main) score 57

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:32.201545+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:27:53.646475+00:00, confidence not recorded.
  - readme: https://github.com/yandexdataschool/Practical_DL (fetched 2026-08-28T04:05:32.201545+00:00, sha 90b2f5d84d98)
- Data as of 2026-08-30T08:39:29.467469+00:00.