# Sentdex/NNfSiX

Neural Networks from Scratch in various programming languages

Repository: https://github.com/Sentdex/NNfSiX
Canonical: https://ross.abutalabs.com/products/nnfsix
Homepage: https://nnfs.io
Language: C++
License: MIT
License Family: permissive
Last push: 2023-09-24T22:01:43+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": 2330, "days_push": 1074, "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 1598, forks 402 (observed 2026-08-28T04:05:09.395933+00:00)

## What it is
Companion code repository for the 'Neural Networks from Scratch' book and video series, implementing neural networks without libraries in multiple programming languages. It serves as a community-driven translation of the Python tutorial code into languages like C++, Java, and others.

## Use cases
- learn how neural networks work internally without frameworks
- follow along with the NNfSiX book in a language other than Python
- see how backpropagation and activation functions are implemented from scratch
- compare neural network implementations across programming languages
- contribute translations of tutorial code to a new language

## When to choose
- you want to deeply understand deep learning fundamentals by building networks without libraries
- you prefer following the Sentdex tutorials in C++, Java, or another supported language
- you want reference implementations of neurons, layers, loss, and optimizers from scratch

## When to avoid
- you need a production-ready deep learning framework with GPU acceleration
- you want pre-trained models or high-level APIs like PyTorch or TensorFlow
- you need complete, well-tested implementations rather than educational code

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, tutorials
- platform: python, cpp, cross-platform
- tags: neural-networks, from-scratch, educational, multi-language, book-companion

## Member repositories
- Sentdex/NNfSiX (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:09.395933+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 2026-08-30T03:53:15.695500+00:00, confidence not recorded.
  - readme: https://github.com/Sentdex/NNfSiX (fetched 2026-08-28T04:05:09.395933+00:00, sha 0e14e4655101)
  - homepage: https://nnfs.io (fetched 2026-08-29T11:24:32.592719+00:00, sha f3f334af6779)
- Data as of 2026-08-30T08:39:29.467469+00:00.