# sachinruk/deepschool.io

Deep Learning tutorials in jupyter notebooks.

Repository: https://github.com/sachinruk/deepschool.io
Canonical: https://ross.abutalabs.com/products/deepschoolio
Language: Jupyter Notebook
License: NOASSERTION
License Family: other
Topics: deep-learning, keras, python3, jupyter-notebook
Last push: 2023-03-25T01:06:42+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": 3559, "days_push": 1258, "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 1808, forks 503 (observed 2026-08-28T04:05:39.283862+00:00)

## What it is
DeepSchool.io is a collection of open-source deep learning tutorials delivered as Jupyter notebooks, covering data science with Pandas, deep learning with Keras, and Bayesian learning with PyMC3. The notebooks are designed to run on Google Colab with minimal code and math, making deep learning practical and accessible on laptops.

## Use cases
- learn deep learning with keras through hands-on notebooks
- beginner-friendly introduction to neural networks
- learn bayesian modeling with pymc3
- practice pandas and data science basics
- run deep learning tutorials on google colab for free
- supplement a machine learning course with practical examples

## When to choose
- you want minimal-code, practical deep learning tutorials that run on free cloud GPUs
- you prefer learning through interactive jupyter notebooks
- you are a beginner who wants to minimize the mathematics involved

## When to avoid
- you need production-grade deep learning code or a maintained library
- you require comprehensive, up-to-date coverage of modern architectures like transformers
- you need a structured curriculum with active support - the project appears to be in maintenance mode

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: deep-learning, machine-learning, data-science
- domain: deep-learning, machine-learning, data-science, tutorials
- platform: python, cross-platform
- tags: jupyter-notebooks, keras, tutorials, education, bayesian-learning, pymc3, google-colab

## Member repositories
- sachinruk/deepschool.io (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:39.283862+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 2026-08-30T03:21:23.570836+00:00, confidence not recorded.
  - readme: https://github.com/sachinruk/deepschool.io (fetched 2026-08-28T04:05:39.283862+00:00, sha 7d10c408dd40)
- Data as of 2026-08-30T08:39:29.467469+00:00.