Made With ML
Learn to build, deploy and iterate production ML apps
Bare-bones NumPy implementations of core ML algorithms
ML From Scratch implements fundamental machine learning models and algorithms — regression, clustering, neural networks and more — in bare-bones NumPy for maximum accessibility. It is for learners and practitioners who want to see the math turned into working code without framework magic.
Each algorithm lives in a self-contained Python file with minimal dependencies, exposing fit/predict style APIs. You read or run the code, then swap in your own datasets or extend the implementations to experiment.
16 Cool GitHub Repos You WILL Use (no pressure)
Learn to build, deploy and iterate production ML apps
Runs huge models on small GPUs by streaming layers
Pretrained foundation model for forecasting numeric time-series data
Command-line video downloader built to be wired into automated workflows
Open agent skills for documents, PDFs and office files
Spec-driven development toolkit that makes agents agree before coding