# eriklindernoren/ML-From-Scratch

> A collection of machine learning models and algorithms implemented from scratch in NumPy, from linear regression to deep learning, focused on showing how they work internally rather than on performance.

- Magnitude: 2.7 out of 10 — Steady
- Stars: 33,233 total · +7 stars measured 2026-11-01, 11:01–14:31 UTC, ≈ 15 by evening
- Star trust: star growth looks organic
- Category: Learning & lists · Language: Python · License: MIT · Created: 2017-02-05 · Last push: 2023-10-15
- GitHub: https://github.com/eriklindernoren/ML-From-Scratch · Page: https://gitnova.dev/en/r/eriklindernoren/ML-From-Scratch

## Useful for

- Study how a CNN, GAN or DBSCAN is implemented step by step in NumPy
- Run example scripts to train a model on MNIST or CartPole and inspect the output
- Use the code as a reference when writing your own ML algorithm from scratch

## Why it’s here

- Star-counter measurements on 2026-11-01 (UTC), 11:01–14:31: 33226 → 33233 stars (+7). This is the change over that interval.
- Estimated end-of-day forecast: about +15 stars, using observed gains and the previous day.
- Over the last two days the pace is 1.7× that of the previous week and a half.
- GitHub Trending Python today: #16, +36 stars.
- About 9 forks a day — people are taking the code.
- Recent forks include notable developers: @vishalbelsare (256 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 5,530
- Issues and pull requests: 144
- Watchers: 969
- Average over the last week: 17 per day
- Usual pace: 14 per day
- Stars in the last hour (measured): 1

## Stars per day, last 30 days (oldest → newest, today is partial)

2026-10-03 … 2026-11-01: 2, 6, 6, 10, 1, 4, 7, 5, 6, 10, 6, 7, 10, 6, 5, 3, 10, 4, 4, 6, 74, 26, 8, 9, 8, 8, 6, 37, 35, 7

## Spotted in now

- GitHub Trending Python today: #16, +36 stars

## Similar by description

1. **jyotipmahes/ML-Interview-Prep** — 5.1 · Early signal · Learning & lists · Jupyter Notebook · +3 stars measured 2026-11-01, 13:47–14:29 UTC, ≈ 23 by evening
   A Jupyter notebook collection with from-scratch implementations of core ML interview algorithms, including linear/logistic regression, K-Means, KNN, MLP, LayerNorm, self-attention, LoRA, and BPE, with math formulations and tests.
   Full card: https://gitnova.dev/en/r/jyotipmahes/ML-Interview-Prep.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-11-01 14:39 UTC, updated every 30 minutes.