By rescaling atomic pair distances with element-pair-specific parameters, the authors make one shared radial function serve all elements, yielding an ultra-small machine learning interatomic potential with accuracy close to large neural network models.
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
-
Global Universal Scaling and Ultra-Small Parameterization in Machine Learning Interatomic Potentials with Super-Linearity
By rescaling atomic pair distances with element-pair-specific parameters, the authors make one shared radial function serve all elements, yielding an ultra-small machine learning interatomic potential with accuracy close to large neural network models.