Skip to content
Day 43 since launch: Best Productivity Resources went live on 25 August 2026. Day 43 is live with yesterday's additions in the latest roundup!

Course

ML From Scratch

Bare bones NumPy implementations of machine learning models and algorithms.

Built with love by Shushant Lakhyani. Building bestproductivityresources.com

Screenshot or bookmark this page so you find it later, then share it with your network.

What is ML From Scratch?

ML-From-Scratch is a collection of accessible, bare-bones NumPy implementations of machine learning models and algorithms — from linear regression to deep learning — with a focus on readability and learning.

Pros

  • Covers a huge range of algorithms
  • Readable NumPy-only code
  • Great bridge from theory to practice

Cons

  • Not optimised for performance
  • Learning resource, not a library to ship

Who should use ML From Scratch

Students and engineers learning how ML algorithms work under the hood.

Who may not need it

Practitioners needing production-grade performance.

ML From Scratch alternatives

Similar resources to ML From Scratch, picked from the directory.

Free alternatives to ML From Scratch

Free resources that cover similar ground.

FinAI Research

Evidence-first AI workflow for economic and financial research: from topic to verifiable LaTeX draft.

AI ToolResearchmacOS, WindowsFree

Featured on Best Productivity Resources

Made ML From Scratch? Add this free badge to your website or README. It links to this page.

Featured on Best Productivity Resources
<a href="https://bestproductivityresources.com/resources/ml-from-scratch" target="_blank" rel="noopener"><img src="https://bestproductivityresources.com/badges/featured-light.svg" alt="Featured on Best Productivity Resources" width="250" height="54" /></a>

Weekly newsletter

Join my email newsletter for the newest tools and visual guides.

Discover new tools and websites, plus fresh visual guides delivered every Monday.

Open stats

Live traffic, fully public

This site's analytics are open for everyone to see.