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 1803.01588cs.LGcs.AI
收藏

N体网络:学习原子势的协变分层神经网络结构

N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials

The University of Chicago(芝加哥大学)

Risi Kondor

摘要:

我们描述了N体网络,一个神经网络架构,用于学习复杂的多体物理系统的行为和属性。我们的具体应用是学习用于分子动力学模拟的原子势能面。我们的架构是新颖的,因为(a)它是基于多体系统到子系统的分层分解,(b)网络的激活对应于每个子系统的内部状态,(c)网络中的“神经元”被明确地构造,以保证每个激活都是旋转协变的,(d)神经元完全在傅立叶空间中操作,非线性通过张量积和Clebsch-Gordan分解实现。作为我们网络描述的一部分,我们给出了网络权重与激活交互的方式的特征,以确保保持协方差属性。

英文摘要:

We describe N-body networks, a neural network architecture for learning the behavior and properties of complex many body physical systems. Our specific application is to learn atomic potential energy surfaces for use in molecular dynamics simulations. Our architecture is novel in that (a) it is based on a hierarchical decomposition of the many body system into subsytems, (b) the activations of the network correspond to the internal state of each subsystem, (c) the "neurons" in the network are constructed explicitly so as to guarantee that each of the activations is covariant to rotations, (d) the neurons operate entirely in Fourier space, and the nonlinearities are realized by tensor products followed by Clebsch-Gordan decompositions. As part of the description of our network, we give a characterization of what way the weights of the network may interact with the activations so as to ensure that the covariance property is maintained.

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。

↑