Toward an artificial intelligence physicist for unsupervised learning

Tailin Wu and Max Tegmark
Phys. Rev. E 100, 033311 – Published 19 September 2019

Abstract

We investigate opportunities and challenges for improving unsupervised machine learning using four common strategies with a long history in physics: divide and conquer, Occam's razor, unification, and lifelong learning. Instead of using one model to learn everything, we propose a paradigm centered around the learning and manipulation of theories, which parsimoniously predict both aspects of the future (from past observations) and the domain in which these predictions are accurate. Specifically, we propose a generalized mean loss to encourage each theory to specialize in its comparatively advantageous domain, and a differentiable description length objective to downweight bad data and “snap” learned theories into simple symbolic formulas. Theories are stored in a “theory hub,” which continuously unifies learned theories and can propose theories when encountering new environments. We test our implementation, the toy “artificial intelligence physicist” learning agent, on a suite of increasingly complex physics environments. From unsupervised observation of trajectories through worlds involving random combinations of gravity, electromagnetism, harmonic motion, and elastic bounces, our agent typically learns faster and produces mean-squared prediction errors about a billion times smaller than a standard feedforward neural net of comparable complexity, typically recovering integer and rational theory parameters exactly. Our agent successfully identifies domains with different laws of motion also for a nonlinear chaotic double pendulum in a piecewise constant force field.

  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
  • Figure
  • Received 20 April 2019

DOI:https://doi.org/10.1103/PhysRevE.100.033311

©2019 American Physical Society

Physics Subject Headings (PhySH)

NetworksNonlinear Dynamics

Authors & Affiliations

Tailin Wu* and Max Tegmark

  • Department of Physics and Center for Brains, Minds, and Machines, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139, USA and Theiss Research, La Jolla, California 92037, USA

  • *tailin@mit.edu

Article Text (Subscription Required)

Click to Expand

References (Subscription Required)

Click to Expand
Issue

Vol. 100, Iss. 3 — September 2019

Reuse & Permissions
Access Options
Author publication services for translation and copyediting assistance advertisement

Authorization Required


×
×

Images

×

Sign up to receive regular email alerts from Physical Review E

Log In

Cancel
×

Search


Article Lookup

Paste a citation or DOI

Enter a citation
×