Name: Discovering symmetry invariants and conserved quantities by interpreting siamese neural networks
Brand: doi.org
SKU: doi-org-71
Availability: OnlineOnly

critic

Discovering symmetry invariants and conserved quantities by interpreting siamese neural networks

preview

Phys. Rev. Research 2, 033499 – Published 25 September 2020 We introduce interpretable siamese neural networks (SNNs) for similarity detection to the field of theoretical physics. More precisely, we apply SNNs to events in special relativity, the transformation of electromagnetic fields, and the motion of particles in a central potential. In these examples, SNNs learn to identify data points belonging to the same event, field configuration, or trajectory of motion. We demonstrate that in the process of learning which data points belong to the same event or field configuration, these SNNs also learn the relevant symmetry invariants and conserved quantities. Such SNNs are highly interpretable, which enables us to reveal the symmetry invariants and conserved quantities without prior knowledge.Published by the American Physical Society under the terms of the license. Further distribution of this work must maintain attribution to the author(s) and the published article's title, journal citation, and DOI.Published by the American Physical SocietyClick to ExpandClick to ExpandIssueSubject AreasOther OptionsSign up to receive regular email alerts from Physical Review ResearchIt is not necessary to obtain permission to reuse thisarticle or its components as it is available under the terms ofthe license.This license permits unrestricted use, distribution, andreproduction in any medium, provided attribution to the author(s) andthe published article's title, journal citation, and DOI aremaintained. Please note that some figures may have been included withpermission from other third parties. It is your responsibility toobtain the proper permission from the rights holder directly forthese figures.Paste a citation or DOIEnter a citation

Phys. Rev. Research 2, 033499 – Published 25 September 2020 We introduce interpretable siamese neural networks (SNNs) for similarity detection to the field of theoretical physics. More precisely, we apply SNNs to events in special relativity, the transformation of electromagnetic fields, and the motion of particles in a central potential. In these examples, SNNs learn to identify data points belonging to the same event, field configuration, or trajectory of motion. We demonstrate that in the process of learning which data points belong to the same event or field configuration, these SNNs...

public

doi.org

Credible

Speculation

Anecdotal Evidence

Generalization

Stacking the Deck

Appeal to Authority

Straw Man

Slippery Slope

Emotional Appeal

Red Herring

False Dilemma

Illogical

Moral Equivalency

Ad Hominem

Correlation w/o Causation

Semantics

Begging the Question

Faulty Analogy

Non Sequitur

Bandwagon

Dogmatism

Failing Occam's Razor

Biased

Pure Opinion

Hit Piece

Racial Bias

National Bias

Religious Bias

Financial Incentive

Political Agenda

Gender Bias

Misused Image/Video

Study Misinterpreted

Mistake

Misused Term

Science Misrepresented

Factual Error

Satire

Surface Level

Lack of Reliable Sources

Sensational

Not Credible

Investigative

Balanced

Well Sourced

Great Context

sports

entertainment

U.S.

international

business

technology

science

culture

politics

media

health

Discovering symmetry invariants and conserved quantities by interpreting siamese neural networks

No article scores yet.

CRITIC REVIEWS

PUBLIC REVIEWS