imetallica / machinex

Machine Learning in Elixir (initial stages)

Machinex

Machine Learning with Elixir

Introduction

Machinex plans to be a machine learning library running on top of Elixir. The idea behind Machinex is to allow the user to program in native Elixir and deploy with C/CUDA backends, which are faster than pure Elixir.

We all are aware that Elixir and Erlang/OTP for that matter are not good with computations, but are great with logic and abstraction. So, the implementation of Machinex reflects my desire to have great language abstractions to run machine learning code.

The library is not ready yet, but I've set a small TODO list of what's going to be implemented. This might change as I'm doing this library as I'm learning ML.

• Complex numbers [OK]
• BLAS [In progress]
• Supervised Learning
• Unsupervised Learning
• Deep Learning

Installation

If available in Hex, the package can be installed by adding machinex to your list of dependencies in mix.exs:

def deps do
  [{:machinex, "~> 0.1.0"}]
end

Documentation can be generated with ExDoc and published on HexDocs. Once published, the docs can be found at https://hexdocs.pm/machinex.