# carefree0910/MachineLearning

Machine learning algorithms implemented by pure numpy

Repository: https://github.com/carefree0910/MachineLearning
Canonical: https://ross.abutalabs.com/products/carefree0910-machinelearning
Homepage: https://mlblog.carefree0910.me
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: numpy, machine-learning, deep-learning, visualization, tensorflow, pytorch
Last push: 2023-04-17T11:59:48+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": 3636, "days_push": 1234, "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 1094, forks 714 (observed 2026-08-28T04:03:33.845621+00:00)

## What it is
An educational Python machine learning package implementing classic ML algorithms (Naive Bayes, decision trees, SVM, neural networks, CNNs) from scratch in pure NumPy, with optional TensorFlow and PyTorch backends. It is accompanied by blog posts and articles explaining the theory and implementation details.

## Use cases
- learn how machine learning algorithms work by reading from-scratch numpy implementations
- study neural network and CNN backpropagation without a framework
- compare numpy, tensorflow, and pytorch implementations of the same models
- find educational material explaining SVMs and decision trees
- use simple ML implementations for teaching or coursework

## When to choose
- you want to understand ML algorithms at the implementation level rather than just call a library
- you are teaching or learning machine learning fundamentals with minimal dependencies
- you want readable reference implementations of classic algorithms like SVM, decision trees, and neural networks

## When to avoid
- you need production-grade performance or the latest model architectures
- you want a maintained, feature-rich ML framework for real projects
- you need GPU-optimized training pipelines or ecosystem tooling

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, data-visualization
- domain: machine-learning, deep-learning, education, tutorials
- platform: python
- tags: numpy, educational, from-scratch-implementations, jupyter-notebook, tensorflow, pytorch

## Member repositories
- carefree0910/MachineLearning (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:33.845621+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 2026-08-30T06:47:28.822196+00:00, confidence not recorded.
  - readme: https://github.com/carefree0910/MachineLearning (fetched 2026-08-28T04:03:33.845621+00:00, sha 0d93e183f55e)
  - homepage: https://mlblog.carefree0910.me (fetched 2026-08-29T12:50:33.407577+00:00, sha 75eb093b57f8)
- Data as of 2026-08-30T08:39:29.467469+00:00.