Learning a physical system's energy from data is shown to work better when the data include dissipation, because dissipation breaks the hidden-symmetry (Casimir) degeneracy that pure reversible dynamics cannot reveal.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.data-an 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Learning Physics from Data: a Thermodynamic Interpretation
Learning a physical system's energy from data is shown to work better when the data include dissipation, because dissipation breaks the hidden-symmetry (Casimir) degeneracy that pure reversible dynamics cannot reveal.