Integrating Machine Learning Models with Elixir Using Nx

Andrés Alejos presents an approach to integrating machine learning, specifically decision trees, with Elixir. Decision trees are a class of supervised machine learning techniques suitable for structured tabular data, such as that found in spreadsheets and databases. The session introduces EXGBoost + Mockingjay, a combination of a Gradient Boosted Decision Tree library with a library that converts trained trees into Nx tensor operations. Alejos explains how these libraries function, showcases examples of their use, and explores the potential for training and deploying decision trees in a scalable production environment using Nx Serving and Phoenix web apps. The talk concludes by looking at the future of machine learning in Elixir and emphasizing the benefits of bringing advanced machine learning techniques to the language.