LATTE: an atomic environment descriptor based on Cartesian tensor contractions

no code implementations • 13 May 2024 • Franco Pellegrini, Stefano de Gironcoli, Emine Küçükbenli

We propose a new descriptor for local atomic environments, to be used in combination with machine learning models for the construction of interatomic potentials.

PANNA 2.0: Efficient neural network interatomic potentials and new architectures

1 code implementation • 19 May 2023 • Franco Pellegrini, Ruggero Lot, Yusuf Shaidu, Emine Küçükbenli

We present the latest release of PANNA 2. 0 (Properties from Artificial Neural Network Architectures), a code for the generation of neural network interatomic potentials based on local atomic descriptors and multilayer perceptrons.

Efficient Neural Network