# joanbruna/stat212b

Topics Course on Deep Learning UC Berkeley

Repository: https://github.com/joanbruna/stat212b
Canonical: https://ross.abutalabs.com/products/stat212b
License Family: other
Last push: 2017-10-28T16:00:30+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": 3899, "days_push": 3231, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1300, forks 299 (observed 2026-08-28T04:04:17.585284+00:00)

## What it is
A UC Berkeley Statistics topics course (Spring 2016) on deep learning, with lecture notes, syllabus, and reading lists covering CNNs, scattering transforms, and deep unsupervised learning. It is educational material rather than software.

## Use cases
- learn the mathematical theory behind convolutional neural networks
- study scattering transforms and group invariance in deep learning
- find readings on variational autoencoders and GANs
- understand non-convex optimization for deep networks
- self-study a graduate-level deep learning course

## When to choose
- you want theory-focused lecture notes on CNNs and unsupervised deep learning
- you prefer mathematical treatments like scattering networks and stability analysis
- you need curated reading lists from a 2016-era graduate course

## When to avoid
- you need runnable code or a software library
- you want up-to-date coverage of modern deep learning methods
- you need maintained material with active support

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: deep-learning, machine-learning
- domain: deep-learning, machine-learning, tutorials
- platform: cross-platform
- tags: course-materials, lecture-notes, uc-berkeley, statistics, cnn, unsupervised-learning

## Member repositories
- joanbruna/stat212b (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:17.585284+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 2026-08-30T04:52:18.947314+00:00, confidence not recorded.
  - readme: https://github.com/joanbruna/stat212b (fetched 2026-08-28T04:04:17.585284+00:00, sha dccd156d0afc)
- Data as of 2026-08-30T08:39:29.467469+00:00.