arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.00092math.DScs.LG
收藏

GFINNs:用于确定性和随机动力系统的GENERIC形式化信息神经网络

GFINNs: GENERIC Formalism Informed Neural Networks for Deterministic and Stochastic Dynamical Systems

Brown University(布朗大学)

Zhen Zhang, Yeonjong Shin, George Em Karniadakis

摘要:

我们提出的GENERIC形式主义知情的神经网络(GFINNs),遵守对称退化条件的GENERIC形式主义。GFINN包括两个模块,每个模块包含两个组件。我们使用一个神经网络,其架构的设计,以满足所需的条件,每个组件建模。组件式架构设计提供了将可用物理信息利用到神经网络中的灵活方法。我们从理论上证明了GFINNs有足够的表达能力来学习基本方程,从而建立了通用逼近定理。我们证明了GFINNs的性能在三个模拟问题:气体容器交换热量和体积,热弹性双摆和Langevin动力学。在所有的例子中,GFINNs优于现有的方法,因此表现出良好的精度在确定性和随机系统的预测。

英文摘要:

We propose the GENERIC formalism informed neural networks (GFINNs) that obey the symmetric degeneracy conditions of the GENERIC formalism. GFINNs comprise two modules, each of which contains two components. We model each component using a neural network whose architecture is designed to satisfy the required conditions. The component-wise architecture design provides flexible ways of leveraging available physics information into neural networks. We prove theoretically that GFINNs are sufficiently expressive to learn the underlying equations, hence establishing the universal approximation theorem. We demonstrate the performance of GFINNs in three simulation problems: gas containers exchanging heat and volume, thermoelastic double pendulum and the Langevin dynamics. In all the examples, GFINNs outperform existing methods, hence demonstrating good accuracy in predictions for both deterministic and stochastic systems.

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。

↑