From the 1 of 5 linked papers with an AI index.
5 papers
Using large language models to probe the limits of atom-centered structural descriptors
Michelangelo Domina, Michele Ceriotti
The paper uses large language models to find atomic structures that cannot be distinguished by atom‑centered symmetry‑invariant descriptors even when clusters of up to seven neighb…
How unconstrained machine-learning models learn physical symmetries
Michelangelo Domina, Joseph William Abbott, Paolo Pegolo +2
The requirement of generating predictions that exactly fulfill the fundamental symmetry of the corresponding physical quantities has profoundly shaped the development of machine-le…
Resolving the Body-Order Paradox of Machine Learning Interatomic Potentials
Sanggyu Chong, Tong Jiang, Michelangelo Domina +4
In many cases, the predictions of machine learning interatomic potentials (MLIPs) can be interpreted as a sum of body-ordered contributions, which is explicit when the model is dir…
Representing spherical tensors with scalar-based machine-learning models
Michelangelo Domina, Filippo Bigi, Paolo Pegolo +1
Rotational symmetry plays a central role in physics, providing an elegant framework to describe how the properties of 3D objects -- from atoms to the macroscopic scale -- transform…
A general formalism for machine-learning models based on multipolar-spherical harmonics
Michelangelo Domina, Stefano Sanvito
The formulation of descriptors of the local chemical environment, enabling the construction of machine-learning models, is usually obtained by studying the properties of the expans…