基础(线性代数)
计算
计算机科学
基函数
基准集
集合(抽象数据类型)
卷积神经网络
深度学习
波函数
功能(生物学)
系列(地层学)
人工神经网络
人工智能
算法
数学
物理
量子力学
几何学
程序设计语言
分子
古生物学
生物
进化生物学
作者
Pavlo Bilous,Adriana Pálffy,Florian Marquardt
出处
期刊:Cornell University - arXiv
日期:2022-01-01
标识
DOI:10.48550/arxiv.2209.05867
摘要
High-precision atomic structure calculations require accurate modelling of electronic correlations typically addressed via the configuration interaction (CI) problem on a multiconfiguration wave function expansion. The latter can easily become challenging or infeasibly large even for advanced supercomputers. Here we develop a deep-learning approach which allows to preselect the most relevant configurations out of large CI basis sets until the targeted energy precision is achieved. The large CI computation is thereby replaced by a series of smaller ones performed on an iteratively expanding basis subset managed by a neural network. While dense architectures as used in quantum chemistry fail, we show that a convolutional neural network naturally accounts for the physical structure of the basis set and allows for robust and accurate CI calculations. The method was benchmarked on basis sets of moderate size allowing for the direct CI calculation, and further demonstrated on prohibitively large sets where the direct computation is not possible.
科研通智能强力驱动
Strongly Powered by AbleSci AI