In plain words: Physics is simple because its rules depend on only a few things at once, while AI problems seem to need endless detail. It argues machine learning also leans on this "few things matter" rule, and urges physicists to bring their tools to deep learning.
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.
Daniel A. Roberts
arXiv:2104.00008 · hep-th, cs.AI, cs.LG, physics.hist-ph, stat.ML · submitted Mar 31, 2021
abstract · pdf · html · written for a special issue of Machine Learning: Science and Technology as an invited perspective piece
