arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1112.5441physics.comp-phcs.LGphysics.chem-phstat.ML
收藏

用机器学习寻找密度泛函

Finding Density Functionals with Machine Learning

University of California, Irvine(加州大学欧文分校);Technical University of Berlin(柏林工业大学);ETH Zurich(苏黎世联邦理工学院)

John C. Snyder, Matthias Rupp, Katja Hansen, Klaus-Robert Müller, Kieron Burke

摘要:

机器学习用于近似密度泛函。对于一维非相互作用费米子的动能模型问题,在训练密度小于100的情况下,与训练集相似的测试密度的平均绝对误差达到1千卡/摩尔以下.预测器识别测试密度是否在插值区域内。通过主成分分析,投影函数导数可以找到高度精确的自洽密度。我们的方法应用到真正的电子结构问题的挑战进行了讨论。

英文摘要:

Machine learning is used to approximate density functionals. For the model problem of the kinetic energy of non-interacting fermions in 1d, mean absolute errors below 1 kcal/mol on test densities similar to the training set are reached with fewer than 100 training densities. A predictor identifies if a test density is within the interpolation region. Via principal component analysis, a projected functional derivative finds highly accurate self-consistent densities. Challenges for application of our method to real electronic structure problems are discussed.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑