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.
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.
Machine Learning Framework for Hackers
Rust language bindings for TensorFlow.
A machine learning library.
A multilayer feedforward backpropagation neural network library
tedsta/deeplearn-rs [ repo · ]
Deep neural networks in Rust
HAL: a machine learning library that is able to run on Nvidia, OpenCL or CPU BLAS based compute backends. It currently provides stackable classical neural networks, RNN's and soon to be LSTM's. A differentiation of this package is that we are looking to implement RTRL (instead of just BPTT) for the recurrent layers in order to provide a solid framework for online learning. We will also (in the future) be implementing various layers such as unitary RNN's, NTM's and Adaptive Computation time based LSTM's. HAL also comes with the ability to plot and do many basic math operations on arrays.
An Experimental Deep Learning Library
A library for doing maching learning in Rust.
A neural network implementation with a focus on cache-efficiency and sequential performance.
Wrapper for the Fast Artificial Neural Networks library