eriklindernoren/ML-From-Scratch
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
Build with Backblaze B2
SDKs, agent skills, IDE extensions, and reference pipelines from Backblaze Labs. All open source.
Loading star history...
Where it stands
Rank, growth pace and release cadence relative to everything GStars tracks.
Ranks #345 of 1,950 repositories GStars tracks this week (top 18%).
The project lists 6 contributors on GitHub.
Peaked at #96 in the weekly ranking the week of Sep 7, its best in the past year.
Use Cases & Benefits
- Implements fundamental machine learning models and algorithms from scratch using Python and NumPy for educational transparency.
- Provides clear, accessible code to understand inner workings of ML algorithms rather than optimized performance.
- Use for learning and experimenting with core supervised and unsupervised machine learning techniques in Python.
- Use for exploring deep learning architectures like CNNs, GANs, and reinforcement learning with simple, readable implementations.
- Use for studying evolutionary algorithms and genetic algorithms applied to neural networks and optimization problems.
Should you depend on it?
License terms, project hygiene and risks, from GitHub metadata and GStars' snapshots.
License
MIT
Permissive: commercial use, modification and redistribution are allowed with attribution.
Community files
- README: present
Watch-outs
- Warning: No commits in over a year (last push Oct 2023).
- No GitHub releases; pin a commit or tag instead of a release.
General guidance from repository metadata, not legal advice. How we score
From the README
Python implementations of some of the fundamental Machine Learning models and algorithms from scratch.
The purpose of this project is not to produce as optimized and computationally efficient algorithms as possible but rather to present the inner workings of them in a transparent and accessible way.
Daily snapshots
Stars gained per day, and how forks and open issues moved, from GStars' daily snapshots
+640 stars over 83 days across 13 snapshot days; best day +87 on Sep 6.
Forks
5.5K+77
Open issues
81+5
Compared with peers in Deep Learning
Fastest-growing repositories GStars tracks in this cohort for the week of Oct 11, by 7-day star growth
| Repository | Stars | +7d | Health | Last release |
|---|---|---|---|---|
| p-e-w/heretic | 35.1K | +1.5K | 41 | 121 days ago |
| koharu-rs/koharu | 6.1K | +337 | 64 | 22 days ago |
| CorentinJ/Real-Time-Voice-Cloning | 60.2K | +0 | 75 | — |
| eriklindernoren/ML-From-Scratch | 33.0K | +0 | 75 | — |
| NVIDIA-NeMo/Speech | 18.6K | +0 | 57 | 63 days ago |
| GeeeekExplorer/nano-vllm | 15.8K | +0 | 75 | — |
| Category median | 18.6K | +0 | 64 | — |
Discover Repositories
Search across tracked repositories by name or description