Rust for Machine Learning

Introduction: Programs that Learn

A Note for Early Release Readers

With Early Release ebooks, you get books in their earliest form—the author’s raw and unedited content as they write—so you can take advantage of these technologies long before the official release of these titles.

This will be the introduction of the final book. Please note that the GitHub repo will be made active later on.

If you’d like to be actively involved in reviewing and commenting on this draft, please reach out to the editor at [e-mail].

[M]achines of this character can behave in a very complicated manner when the number of units is large.

Alan Turing

When I first started working with machine learning, more than ten years ago, I was fascinated by the idea of systems that can learn from data. At that time, we were building a demand forecasting service for a client, using historical contract and sales data to predict demand for different components in the following year. To help us achieve our goal we brought a data scientist in the team pairing with developers to deliver a testable, production-ready system.

He soon started experimenting with different solutions for the problem, one of them being linear regression, a machine learning technique that predicts numerical outputs based on the data. I wanted to understand the theory behind what we were building, so a colleague and I spent our nights in a 24-hour bakery working through Andrew Ng’s Stanford Machine Learning course. At that time, it ...