# neonwatty/machine-learning-refined

Master the fundamentals of machine learning, deep learning, and mathematical optimization by building key concepts and models from scratch using Python.

Repository: https://github.com/neonwatty/machine-learning-refined
Canonical: https://ross.abutalabs.com/products/machine-learning-refined
Homepage: https://www.mlrefined.com/
Language: Python
License: NOASSERTION
License Family: other
Topics: machine-learning, deep-learning, artificial-intelligence, data-science, jupyter-notebook, numpy, python
Last push: 2026-07-11T21:46:57+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 92, release rhythm 28, longevity 100
- inputs: {"age_days": 3673, "days_push": 53, "days_rel": 264, "gap_med": null, "n_releases_24m": 1}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2258, forks 706 (observed 2026-08-28T04:06:31.573903+00:00)

## What it is
The companion repository for the university textbook 'Machine Learning Refined' (2nd edition), offering free chapter PDFs, Jupyter notebooks, exercises, and lecture slides. It teaches machine learning, deep learning, and mathematical optimization fundamentals by building models from scratch in Python with NumPy.

## Use cases
- learn machine learning fundamentals from scratch in python
- free machine learning textbook pdf
- jupyter notebooks explaining deep learning and optimization
- teach a university machine learning course with slides and exercises
- understand the math behind gradient descent and cost functions
- self-study resource for machine learning with numpy

## When to choose
- you want intuition-first, from-scratch explanations of ML and optimization
- you prefer runnable Python notebooks over framework-heavy tutorials
- you are an instructor needing free PDFs, slides, and exercises for a course

## When to avoid
- you need production-ready ML libraries or pretrained models
- you want a quick high-level framework guide like scikit-learn or PyTorch docs
- you need advanced state-of-the-art topics like LLMs or transformers

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, math, data-science
- domain: machine-learning, deep-learning, artificial-intelligence, data-science, education, tutorials
- platform: python, cross-platform
- tags: textbook, jupyter-notebooks, from-scratch, optimization, free-pdf, university-course

## Member repositories
- neonwatty/machine-learning-refined (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:31.573903+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 2026-08-30T02:43:39.132577+00:00, confidence not recorded.
  - readme: https://github.com/neonwatty/machine-learning-refined (fetched 2026-08-28T04:06:31.573903+00:00, sha e24111a37a1d)
  - homepage: https://www.mlrefined.com/ (fetched 2026-08-29T10:23:30.687306+00:00, sha 5865052382af)
- Data as of 2026-08-30T08:39:29.467469+00:00.