首页|University of Pittsburgh Reports Findings in Machine Learning (Overcoming Inaccu racies in Machine Learning Interatomic Potential Implementation for Ionic Vacanc y Simulations)
University of Pittsburgh Reports Findings in Machine Learning (Overcoming Inaccu racies in Machine Learning Interatomic Potential Implementation for Ionic Vacanc y Simulations)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – New research on Machine Learning is th e subject of a report. According to news reportingout of Pittsburgh, Pennsylvan ia, by NewsRx editors, research stated, “Machine learning interatomicpotentials , particularly ones based on deep neural networks, have taken significant stride s in acceleratingfirst-principles simulations, expanding the length and time sc ales of the simulations with accuracies akin tofirst-principles simulations. No twithstanding their success in accurately describing the physical propertiesof pristine ionic systems with multiple oxidation states, herein we show that an im plementation of deepneural network potentials (DNPs) yield vacancy formation en ergies in MgO with a significant 3 eV error.”
PittsburghPennsylvaniaUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
