# trekhleb/machine-learning-experiments

🤖 Interactive Machine Learning experiments: 🏋️models training + 🎨models demo

Repository: https://github.com/trekhleb/machine-learning-experiments
Canonical: https://ross.abutalabs.com/products/machine-learning-experiments
Homepage: https://trekhleb.dev/machine-learning-experiments/
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: machine-learning, javascript, python, tensorflow, jupyter-notebooks, colab-notebook, colab, ai, artificial-intelligence, keras, numpy
Last push: 2025-11-23T04:22:17+00:00

## Health v2 (maintenance only)
Score: 56/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 53, release rhythm 35, longevity 100
- inputs: {"age_days": 2484, "days_push": 283, "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 1827, forks 331 (observed 2026-08-28T04:05:41.530947+00:00)

## What it is
A collection of interactive machine learning experiments, each pairing a Jupyter/Colab training notebook with a browser-based demo page showing the trained model in action. Models are built primarily with TensorFlow 2 and Keras, and the repo is explicitly a learning playground rather than production-ready code.

## Use cases
- learn machine learning by training models in colab notebooks
- see trained neural network models running in the browser
- interactive machine learning experiments for beginners
- tensorflow keras example notebooks to study
- playground for trying different ml algorithms and datasets
- understand how multilayer perceptrons and other models are trained

## When to choose
- you want hands-on, notebook-driven learning of ML concepts with visual demos
- you prefer TensorFlow/Keras examples you can run in Colab for free
- you want to see models deployed as simple browser demos without setup

## When to avoid
- you need production-ready, optimized, or fine-tuned models
- you want reusable, well-tested ML libraries or pipelines
- you need state-of-the-art model performance without overfitting/underfitting issues

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, data-science
- domain: machine-learning, deep-learning, artificial-intelligence, education, tutorials
- platform: python, browser, cross-platform
- tags: tensorflow, keras, jupyter-notebook, google-colab, interactive-demos, neural-networks, supervised-learning, sandbox, educational-notebooks, web-server

## Member repositories
- trekhleb/machine-learning-experiments (main) score 56

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:41.530947+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 2026-08-30T03:19:32.849672+00:00, confidence not recorded.
  - readme: https://github.com/trekhleb/machine-learning-experiments (fetched 2026-08-28T04:05:41.530947+00:00, sha 93c24ad78f26)
  - homepage: https://trekhleb.dev/machine-learning-experiments/ (fetched 2026-08-29T10:58:41.331517+00:00, sha 9fc254b52378)
- Data as of 2026-08-30T08:39:29.467469+00:00.