The Physics of Machine Learning: An Intuitive Introduction for the Physical Scientist

TL;DR

This paper provides an intuitive, physics-based understanding of machine learning algorithms, connecting energy-based models to physical systems, and introduces practical neural network training methods for physical scientists.

Contribution

It offers a physics-inspired perspective on machine learning, bridging concepts like the Ising model with neural networks, and includes practical code demonstrations.

Findings

Energy-based models relate to physical systems like the Ising model.

Neural network training can be understood through physical intuition.

Practical code examples illustrate training neural networks with gradient descent.

Abstract

This article is intended for physical scientists who wish to gain deeper insights into machine learning algorithms which we present via the domain they know best, physics. We begin with a review of two energy-based machine learning algorithms, Hopfield networks and Boltzmann machines, and their connection to the Ising model. This serves as a foundation to understand the phenomenon of learning more generally. Equipped with this intuition we then delve into additional, more "practical," machine learning architectures including feedforward neural networks, convolutional neural networks, and autoencoders. We also provide code that explicitly demonstrates training a neural network with gradient descent.