Why is AI hard and Physics simple?

TL;DR

This paper explores the fundamental differences between AI and physics, proposing that physical intuition and principles like sparsity can inform AI research, and calls for physicists to contribute to AI theory development.

Contribution

It introduces the idea that physics principles, especially sparsity, can be applied to understand and advance AI, encouraging physicists to engage with AI research.

Findings

AI is inherently complex, while physics relies on simplicity and intuition.

The principle of sparsity links the core ideas of physics and machine learning.

A forthcoming book aims to formalize deep learning principles from a physics perspective.

Abstract

We discuss why AI is hard and why physics is simple. We discuss how physical intuition and the approach of theoretical physics can be brought to bear on the field of artificial intelligence and specifically machine learning. We suggest that the underlying project of machine learning and the underlying project of physics are strongly coupled through the principle of sparsity, and we call upon theoretical physicists to work on AI as physicists. As a first step in that direction, we discuss an upcoming book on the principles of deep learning theory that attempts to realize this approach.