Consistent with recent deep learning trends, the Rust community has followed suit by building several neural network libraries.

Leaf made a huge splash in the community and included great resources like the Leaf Book and talks like this one. Unfortunately the team behind Leaf moved on, but there is interest and a small amount of activity in possibly reviving a fork.

Taking a page from python’s scikit-learn project, rusty-machine is one of the most actively developed ML crates in the Rust ecosystem. It also powers Learning Machines, a set of interactive tutorials on machine learning, and this presentation provides a solid introduction.

And check out the much newer alumina crate, the backbone of the easy-to-use “super resolution” image enhancer rusty_sr.

Other neural network libraries have been created, but often exist as experimental projects. Some of the projects listed hear appear to be inactive, but are still listed to serve as an inspiration for any future projects.