# d2l-ai/berkeley-stat-157

Homepage for STAT 157 at UC Berkeley

Repository: https://github.com/d2l-ai/berkeley-stat-157
Canonical: https://ross.abutalabs.com/products/berkeley-stat-157
Homepage: https://courses.d2l.ai/berkeley-stat-157/index.html
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2021-02-16T00:35:45+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2815, "days_push": 2025, "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 4005, forks 1510 (observed 2026-08-28T04:08:32.168665+00:00)

## What it is
Course homepage and materials for STAT 157, an Introduction to Deep Learning class taught at UC Berkeley in Spring 2019 by Alex Smola and Mu Li. It includes lecture slides, videos, Jupyter notebooks, homework assignments, and solutions built around the Dive into Deep Learning (D2L) book.

## Use cases
- learn deep learning from scratch
- find a university-level deep learning course with homework
- get jupyter notebooks for practicing neural networks
- study deep learning theory with hands-on implementation
- self-study an introduction to deep learning course
- find lecture slides and videos on deep learning

## When to choose
- you want a structured, semester-long introduction to deep learning with assignments
- you prefer learning through runnable Jupyter notebooks
- you want free lecture videos and slides from Berkeley instructors

## When to avoid
- you need up-to-date material covering modern architectures like transformers or LLMs
- you want a maintained library or tool rather than course content
- you need a framework-agnostic or PyTorch-only curriculum (this course used MXNet)

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning, data-science
- domain: deep-learning, machine-learning, education, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, course-materials, uc-berkeley, mxnet, d2l, lectures, homework

## Member repositories
- d2l-ai/berkeley-stat-157 (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:32.168665+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 2026-08-29T18:24:04.712310+00:00, confidence not recorded.
  - readme: https://github.com/d2l-ai/berkeley-stat-157 (fetched 2026-08-28T04:08:32.168665+00:00, sha e4b859902edb)
  - homepage: https://courses.d2l.ai/berkeley-stat-157/index.html (fetched 2026-08-29T09:17:10.126883+00:00, sha 42c094005df0)
  - site_page: https://d2l.ai/chapter_installation/index.html (fetched 2026-08-29T09:17:10.136178+00:00, sha 6ebdfa9bec4e)
  - site_page: https://courses.d2l.ai/berkeley-stat-157/faq.html (fetched 2026-08-29T09:17:10.138188+00:00, sha 94f5fa708316)
- Data as of 2026-08-30T08:39:29.467469+00:00.