Jupyter Notebook · MIT
ml-from-scratch-book/code
Companion code for Machine Learning From Scratch — 10 core ML algorithms built from scratch with NumPy, compared with Scikit-learn and PyTorch.
★ 322
Stars
33 forks · 0 open issues
−1.0/wk
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
13.2
Momentum / 100
see the breakdown below
6mo ago
Created
last push 3mo ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 0.0 | −1.0/wk, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran -0.25× the monthly pace |
| Freshness | 15 | 5.9 | last push 3mo ago; decays to zero at 180 days |
| Scale | 15 | 7.3 | 322 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 13.2 | sum of the above |
Detail
| Topics | artificial-intelligencedata-sciencedeep-learningeducationfrom-scratch-implementationfrom-scratch-in-pythonfrom-scratch-mlmachine-learningmachine-learning-algorithmsmlneural-networkpythonpytorchroadmapscikit-learnxgboost-algorithm |
| Matched on | Learning & Roadmaps (roadmap) |
| Short window | +-1 stars over 7 days = -0.1/day |
| Long window | +15 stars over 26 days = 0.6/day |
| Lifetime average | 1.69 stars/day over 190 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |