Bundling in Molecular Dynamics Simulations to Improve Generalization Performance in High-Dimensional Neural Network Potentials

<p>High dimensional neural network potential (HDNNP) is interested as an alternative to classical force field calculations by data-driven approach. HDNNP has an advantage over classical force field calculation, such as being able to handle chemical reactions, but there are many points yet to be understood with respect to the chemical transferability in particular for non-organic compounds. In this paper, we focused on Au₁₃⁺ and Au₁₁⁺ clusters and showed that the energy of clusters of different sizes can be predicted by HDNNP with semi-quantitative accuracy.</p>

Bundling in Molecular Dynamics Simulations to Improve Generalization Performance in High-Dimensional Neural Network Potentials

<p>High dimensional neural network potential (HDNNP) is interested as an alternative to classical force field calculations by data-driven approach. HDNNP has an advantage over classical force field calculation, such as being able to handle chemical reactions, but there are many points yet to be understood with respect to the chemical transferability in particular for non-organic compounds. In this paper, we focused on Au₁₃⁺ and Au₁₁⁺ clusters and showed that the energy of clusters of different sizes can be predicted by HDNNP with semi-quantitative accuracy.</p>

Parametrization of nanoparticles: development of full-particle nanodescriptors

A set of novel, theoretical full-particle descriptors for modeling, grouping or read-across of metal oxide NP properties and biological activity was developed based on the force-field calculation of the potential energies of whole NPs.