# mattm/simple-neural-network

A simple Python script showing how the backpropagation algorithm works.

Repository: https://github.com/mattm/simple-neural-network
Canonical: https://ross.abutalabs.com/products/simple-neural-network
Language: Python
License Family: other
Last push: 2025-01-14T17:59:37+00:00

## Health v2 (maintenance only)
Score: 33/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 1, release rhythm 35, longevity 100
- inputs: {"age_days": 4190, "days_push": 596, "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 1093, forks 546 (observed 2026-08-28T04:03:33.756703+00:00)

## What it is
A small Python script that demonstrates how the backpropagation algorithm works in a neural network, accompanying a step-by-step blog post. It is educational example code rather than a reusable library.

## Use cases
- learn how backpropagation works step by step
- understand neural network gradient calculations
- follow along with a backpropagation tutorial
- see a minimal neural network implemented from scratch in Python
- teach deep learning fundamentals with simple code

## When to choose
- you want to understand the math behind backpropagation with readable code
- you need a tiny from-scratch example to study or teach
- you are following the author's step-by-step backpropagation blog post

## When to avoid
- you need a production-ready neural network framework
- you want GPU acceleration or performance
- you need a maintained library with tests, license clarity, or an API

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, developer-tools
- domain: machine-learning, deep-learning, education, tutorials
- platform: python, cross-platform
- tags: backpropagation, neural-network, educational, example-code, no-dependencies

## Member repositories
- mattm/simple-neural-network (main) score 33

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:33.756703+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 2026-08-30T06:48:57.628710+00:00, confidence not recorded.
  - readme: https://github.com/mattm/simple-neural-network (fetched 2026-08-28T04:03:33.756703+00:00, sha 41abdf20afa4)
- Data as of 2026-08-30T08:39:29.467469+00:00.