# tensorflow/playground

Play with neural networks!

Repository: https://github.com/tensorflow/playground
Canonical: https://ross.abutalabs.com/products/playground
Homepage: http://playground.tensorflow.org
Language: TypeScript
License: Apache-2.0
License Family: permissive
Last push: 2026-06-10T04:53:49+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 35, longevity 100
- inputs: {"age_days": 3803, "days_push": 84, "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 12999, forks 2746 (observed 2026-08-28T04:11:00.360433+00:00)

## What it is
An interactive in-browser visualization of neural networks built with TypeScript and d3.js, letting users tweak layers, activations, learning rates, and datasets while watching training happen live. It is an educational tool from the TensorFlow ecosystem for building intuition about how neural networks learn.

## Use cases
- learn how neural networks work interactively
- visualize training of a small neural network in the browser
- experiment with activation functions and regularization
- demonstrate overfitting and decision boundaries to students
- teach deep learning concepts in a classroom
- play with classification and regression toy datasets

## When to choose
- you want an intuitive, hands-on introduction to neural networks
- you need a visual teaching aid for deep learning courses
- you want to explore hyperparameter effects without writing code

## When to avoid
- you need to train real models on real datasets
- you want production-grade deep learning tooling
- you need GPU acceleration or large-scale experiments

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: data-visualization, machine-learning, deep-learning
- domain: machine-learning, deep-learning, education, data-visualization
- platform: browser
- tags: neural-networks, interactive-visualization, educational, browser-based, d3js, tensorflow, web, nodejs, typescript

## Member repositories
- tensorflow/playground (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:00.360433+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 2026-08-29T17:13:36.734859+00:00, confidence not recorded.
  - readme: https://github.com/tensorflow/playground (fetched 2026-08-28T04:11:00.360433+00:00, sha 5d330f6482a8)
  - homepage: http://playground.tensorflow.org (fetched 2026-08-29T08:09:41.459359+00:00, sha 3f78cc61d016)
- Data as of 2026-08-30T08:39:29.467469+00:00.