# oreilly-japan/deep-learning-from-scratch

『ゼロから作る Deep Learning』(O'Reilly Japan, 2016)

Repository: https://github.com/oreilly-japan/deep-learning-from-scratch
Canonical: https://ross.abutalabs.com/products/deep-learning-from-scratch
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2024-11-05T06:55:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3717, "days_push": 666, "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 4839, forks 3558 (observed 2026-08-28T04:09:01.243025+00:00)

## What it is
Companion source code repository for the O'Reilly Japan book 'Deep Learning from Scratch' (2016), organized by chapter with Python/NumPy implementations of neural networks. Includes Jupyter notebooks runnable on Amazon SageMaker Studio Lab.

## Use cases
- learn deep learning from scratch in python
- implement neural networks with numpy only
- study backpropagation and gradient descent step by step
- find companion code for the deep learning from scratch book
- run beginner deep learning notebooks in the cloud

## When to choose
- you want to understand deep learning fundamentals by implementing everything from scratch without frameworks
- you are following the O'Reilly book and need its code
- you prefer minimal NumPy/Matplotlib examples over heavy frameworks

## When to avoid
- you need production-ready or GPU-accelerated deep learning with PyTorch or TensorFlow
- you want modern architectures like transformers or large-scale training
- you need maintained library APIs rather than educational code

## Facets
- artifact type: learning-resource
- maturity: stable
- function: deep-learning, machine-learning, data-science
- domain: deep-learning, machine-learning, tutorials, education
- platform: python, cross-platform
- tags: book-companion-code, jupyter-notebook, numpy, neural-networks, educational, japanese

## Member repositories
- oreilly-japan/deep-learning-from-scratch (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:01.243025+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 2026-08-29T18:18:28.622186+00:00, confidence not recorded.
  - readme: https://github.com/oreilly-japan/deep-learning-from-scratch (fetched 2026-08-28T04:09:01.243025+00:00, sha 8d8547c4d2d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.