Neuromorphic computing and artificial intelligence hardware generally aims to emulate
features found in biological neural circuit components and to enable the development of …

With the advent of faster computer processors and especially graphics processing units
(GPUs) over the last few decades, the use of data-intensive machine learning (ML) and …

Classification of molecular structures is a crucial step in molecular dynamics (MD)
simulations to detect various structures and phases within systems. Molecular structures …

Identifying local structural motifs and packing patterns of molecular solids is a challenging
task for both simulation and experiment. We demonstrate two novel approaches to …

Material properties share an intrinsic relationship with their structural attributes, making
inverse design approaches crucial for discovering new materials with desired functionalities …

Complex crystal structures are composed of multiple local environments, and how this type
of order emerges spontaneously during crystal growth has yet to be fully understood. We …

Contemporary materials science has seen an increasing application of various artificial
intelligence techniques in an attempt to accelerate the materials discovery process using …

Identifying key descriptors and understanding important features across different classes of
materials are crucial for machine learning (ML) tools to both predict material properties and …

In this study, we present a graph neural network (GNN)-based learning approach using an
autoencoder setup to derive low-dimensional variables from features observed in …

Molecular dynamics simulations offer detailed insights into atomic motions but face
timescale limitations. Enhanced sampling methods have addressed these challenges but …