arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.05787physics.chem-phphysics.comp-phquant-ph
收藏

机器学习配置交互

Machine Learning Configuration Interaction

J. P. Coe

摘要:

我们提出了机器学习配置交互(MLCI)的概念,人工神经网络的训练飞行预测重要的新配置在一个迭代的选择配置交互过程。我们证明了神经网络可以区分重要和不重要的配置,它没有经过训练,比偶然的要好得多。MLCI然后被用来找到紧凑的波函数一氧化碳在拉伸和平衡的几何形状。我们还考虑了水分子与拉长的债券的多参考问题。并与一级微扰法、随机选择法和蒙特卡罗组态相互作用法的结果进行了比较。与其他串行计算相比,该原型MLCI在精度上具有竞争力,比随机方法收敛的迭代次数少得多,并且需要更少的时间进行更高精度的计算。

英文摘要:

We propose the concept of machine learning configuration interaction (MLCI) whereby an artificial neural network is trained on-the-fly to predict important new configurations in an iterative selected configuration interaction procedure. We demonstrate that the neural network can discriminate between important and unimportant configurations, that it has not been trained on, much better than by chance. MLCI is then used to find compact wavefunctions for carbon monoxide at both stretched and equilibrium geometries. We also consider the multireference problem of the water molecule with elongated bonds. Results are contrasted with those from other ways of selecting configurations: first-order perturbation, random selection and Monte Carlo configuration interaction. Compared with these other serial calculations, this prototype MLCI is competitive in its accuracy, converges in significantly fewer iterations than the stochastic approaches, and requires less time for the higher-accuracy computations.

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。

↑