• Tensorslow seems to be a pure numpy implementation of tensorflow, for whatever that is worth. There is an associated blog where they basically develop it from scratch, teaching you the basics of neural networks on the way.

  • @yamsergey did you know linguistictagger

  • There’s a really nice repo, which implements many different machine learning algorithms from scratch. I’ve been working on a Pythonista-friendly branch, removing dependencies that aren’t available in Pythonista. There are many examples too, including a variety of neural network implementations.

    I think the only supervised learning algorithm I’ve not managed to port (yet!) is SVM. Everything else work very nicely.

    Check it out here: ML-From-Scratch

    To install, clone the repo in Stash, checkout the pythonista branch and copy the mlfromscratch folder to site-packages. Restart Pythonista and have fun!

Internal error.

Oops! Looks like something went wrong!