APS -APS March Meeting 2017 - Event - Construction of interatomic potentials for multicomponent systems with stratified neural networks

摘要

Recent application of neural networks (NNs) to modeling interatomic interactions has shown the learningmachines' encouragingly accurate performance for select elemental and multicomponent systems. In an effort to buildextended libraries of NN-based models we have introduced a hierarchical training in which NNs for multicomponentsystems are obtained by sequential fitting from the bottom up: first unaries, then binaries, and so on. Advantages ofconstructing NN sets with shared parameters include acceleration of the training process and intact description of theconstituent systems. In the test case of the Cu-Pd-Ag ternary and its subsystems, NNs trained in the traditional andstratified fashions are found to have essentially identical accuracy for defect energies, phonon dispersions, formationenergies, etc. The models' robustness is further illustrated via unconstrained evolutionary structure searches in whichthe NN is used for the local optimization of crystal unit cells. The use of NN instead of DFT in these simulationsaccelerates structure prediction by several orders of magnitude. The NN module is available in the MAISE package.