Machine Learning Configuration Interaction
Machine Learning Configuration Interaction
复制标题
DOI：
10.1021/acs.jctc.8b00849
复制
发表时间：
2018-11-01
影响因子：
5.5
通讯作者：
Coe, J. P.
中科院分区：
文献类型：
--
作者：
Coe, J. P.
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。结果与其他方法的选择配置：一阶微扰，随机选择，和Monte Carlo组态相互作用进行了对比。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。
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 wave functions 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.