LIES, a fixed network with logarithm, identity, exponential, and sine activations, recovers exact symbolic formulas from AI Feynman benchmark data more often than comparison methods on a selected 61-equation subset.
Symbolic regression in materials science,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
Sparse Interpretable Deep Learning with LIES Networks for Symbolic Regression
LIES, a fixed network with logarithm, identity, exponential, and sine activations, recovers exact symbolic formulas from AI Feynman benchmark data more often than comparison methods on a selected 61-equation subset.