首页|Emory University Reports Findings in Machine Learning [D-Mach ine Learning to Elevate DFT-Based Potentials and a Force Field to the CCSD(T) Le vel Illustrated for Ethanol]
Emory University Reports Findings in Machine Learning [D-Mach ine Learning to Elevate DFT-Based Potentials and a Force Field to the CCSD(T) Le vel Illustrated for Ethanol]
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 Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news originating from Atlanta, Georgia, by N ewsRx correspondents, research stated, “Progress in machine learning has facilit ated the development of potentials that offer both the accuracy of first-princip les techniques and vast increases in the speed of evaluation. Recently, D-machin e learning has been used to elevate the quality of a potential energy surface (P ES) based on low-level, e.g., density functional theory (DFT) energies and gradi ents to close to the gold-standard coupled cluster level of accuracy.” Our news journalists obtained a quote from the research from Emory University, “ We have demonstrated the success of this approach for molecules, ranging in size from HO to 15-atom acetyl-acetone and tropolone. These were all done using the B3LYP functional. Here, we investigate the generality of this approach for the P BE, M06, M06-2X, and PBE0 + MBD functionals, using ethanol as the example molecu le. Linear regression with permutationally invariant polynomials is used to fit both low-level and correction PESs. These PESs are employed for standard RMSE an alysis for training and test data sets, and then general fidelity tests such as energetics of stationary points, normal-mode frequencies, and torsional potentia ls are examined. We achieve similar improvements in all cases. Interestingly, we obtained significant improvement over DFT gradients where coupled cluster gradi ents were not used to correct the low-level PES.”
AtlantaGeorgiaUnited StatesNorth a nd Central AmericaAlcoholsCyborgsEmerging TechnologiesEthanolEthanolam inesMachine Learning
NETL
NSTL
