# mnielsen/neural-networks-and-deep-learning

Code samples for my book "Neural Networks and Deep Learning"

Repository: https://github.com/mnielsen/neural-networks-and-deep-learning
Canonical: https://ross.abutalabs.com/products/neural-networks-and-deep-learning
Language: Python
License Family: other
Last push: 2024-06-02T11:18:37+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": 5041, "days_push": 822, "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 17888, forks 7090 (observed 2026-08-28T04:11:20.515865+00:00)

## What it is
Code samples accompanying Michael Nielsen's free online book 'Neural Networks and Deep Learning'. It implements neural networks from scratch in Python, including a Theano-based convolutional network example.

## Use cases
- learn how neural networks work from scratch
- follow along with the neural networks and deep learning book
- understand backpropagation with example code
- study a simple handwritten digit classifier
- see how convolutional networks were implemented with Theano

## When to choose
- you are reading Nielsen's book and want its companion code
- you want minimal, readable educational implementations of neural nets

## When to avoid
- you need Python 3 code in this repo (use the community Python 3 fork)
- you need a maintained deep learning framework or production code
- you need Theano compatibility with modern versions

## Facets
- artifact type: learning-resource
- maturity: abandoned
- function: machine-learning, deep-learning
- domain: deep-learning, tutorials
- platform: python
- tags: book-code, theano, educational, neural-networks

## Member repositories
- mnielsen/neural-networks-and-deep-learning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:20.515865+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 2026-08-29T17:02:17.630233+00:00, confidence not recorded.
  - readme: https://github.com/mnielsen/neural-networks-and-deep-learning (fetched 2026-08-28T04:11:20.515865+00:00, sha ce9ecfd2ec1b)
- Data as of 2026-08-30T08:39:29.467469+00:00.