International Journal of Quantum Chemistry · 2007 · 69 citations · 26 references
Natural SciencesChemistryPhysicsComputational ChemistryQuantum ChemistryTheoretical ChemistryAb Initio MethodsDensity Functional TheoryMolecular DynamicsMolecular ModelingMolecular Orbital TheoryMolecular SimulationComputational Molecular ModelingMachine Learning Potential Energy SurfacesMolecular Electrostatic PotentialMolecular Multipole MomentsMolecular Simulation AlgorithmsPolarizability PredictionQuantum Chemical ModelingQuantum Molecular Dynamics
Abstract The HF molecule is a simple polar system that serves as a prototype for developing new potentials. Here we build on earlier work [Liem and Popelier, J Chem Phys 2003, 119, 4560] in which a high‐rank multipolar potential was used to simulate liquid HF. That work was the first example of high‐rank multipole moments (up to hexadecapole) being employed in conjunction with multipolar Ewald summation in a molecular dynamics simulation. This potential is now extended with polarization, which is delivered by artificial neural networks. The neural nets predict how atomic multipole moments change as the position of neighboring molecules vary. This novel approach is successfully tested on the HF dimer in vacuum. © 2007 Wiley Periodicals, Inc. Int J Quantum Chem, 2007
26
An introduction to neural networks
Choice Reviews Online · 1998 · 1.8K citations
Neural network models of potential energy surfaces
Thomas B. Blank, Steven D. Brown, August Calhoun et al. · The Journal of Chemical Physics · 1995 · 499 citations