A composition-only model that applies ReLU to a weighted average of per-element learned parameters predicts band gaps with 0.575 eV MAE and yields chemically interpretable element weights.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.mtrl-sci 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Predicting band gap from chemical composition: A simple learned model for a material property with atypical statistics
A composition-only model that applies ReLU to a weighted average of per-element learned parameters predicts band gaps with 0.575 eV MAE and yields chemically interpretable element weights.