Pith. sign in

REVIEW 1 cited by

Toward an AI Physicist for Unsupervised Learning

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1810.10525 v4 pith:MO2YOI4E submitted 2018-10-24 physics.comp-ph cond-mat.dis-nncs.LG

classification physics.comp-phcond-mat.dis-nncs.LG
keywords learningtheoriesagentproposetheoryunsuperviseddomainenvironments
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original 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 novel 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 novel 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 "AI 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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Discover physical concepts and equations with machine learning

    cs.LG 2024-12 conditional novelty 5.0 of 10

    A VAE+Neural ODE model recovers linear combinations of physical concepts and governing equations for heliocentrism, gravity, Schrödinger mechanics, and a Pauli spin case from simulated data.

Pith tools