Rust for Machine Learning

Chapter 1. The First Neuron

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 1st chapter 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].

I long to accomplish a great and noble task; but it is my chief duty to accomplish small tasks as if they were great and noble.

Helen Keller

Welcome to chapter one. In this chapter we will implement the perceptron, a learning algorithm first developed in 1957 by Frank Rosenblatt and published in 1958 in a paper titled “The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain.” Rosenblatt was inspired by neuroscience and psychology, particularly by how biological neurons might give rise to learning and cognition.

The perceptron introduced several ideas that remain at the foundation of machine learning today. In this chapter, we will focus on two of them: linear classifiers and learning via parameter updates.

We will take a step by step approach. In the first section we will build the intuition using two simple functions, AND and OR, which are familiar to every programmer. In the second section, we shift perspective and explore learning ...