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 2205.14630cs.LG
收藏

物理激活函数(PAFs):一种将物理规律更高效引入物理信息神经网络(PINNs)的方法

Physical Activation Functions (PAFs): An Approach for More Efficient Induction of Physics into Physics-Informed Neural Networks (PINNs)

University of Stavanger(斯塔万格大学)

Jassem Abbasi, Pål Østebø Andersen

AI总结:

针对物理信息神经网络(PINNs)训练难、物理融合效率低的问题,提出源自物理规律的物理激活函数(PAFs),可提升分布外预测精度、缩减75%模型规模、降低1-2个数量级损失并减少迭代次数。

摘要:

近年来,物理信息神经网络(Physics-Informed Neural Networks, PINNs)的发展正试图填补深度学习(Deep Learning, DL)方法与科学计算中解析或数值方法之间的差距。然而,PINNs的训练以及物理模型的最优融合仍存在诸多复杂问题。在此,我们提出了物理激活函数(Physical Activation Functions, PAFs)的概念。该概念提出,无需为所有神经元使用ReLU、tanh和sigmoid等通用激活函数(activation functions, AFs),而是可以采用数学表达式源自所研究现象物理规律的通用激活函数。PAFs的公式可受问题解析解中的项启发。我们证明,PAFs可以由任何与研究现象相关的数学公式推导而来,例如偏微分方程(PDE)系统的初始条件或边界条件。我们在多种偏微分方程上验证了PAFs的优势,包括简谐振动方程、Burgers方程、平流-对流方程以及非均匀扩散方程。PAFs的主要优势在于能够更高效地约束PINNs,并使其与所研究的物理现象及其底层数学模型更好地融合。这种新增的约束显著提升了PINNs对训练分布外测试数据的预测效果。此外,在不同案例中,PAFs的应用使PINNs的模型规模最高减少了75%。在部分案例中,损失项的数值降低了1到2个数量级,这对改进PINNs的训练具有重要意义。求解最优值所需的迭代次数也显著减少。研究结论表明,使用PAFs有助于构建复杂度更低、在更长预测范围内有效性更强的PINNs。

英文摘要:

In recent years, the gap between Deep Learning (DL) methods and analytical or numerical approaches in scientific computing is tried to be filled by the evolution of Physics-Informed Neural Networks (PINNs). However, still, there are many complications in the training of PINNs and optimal interleaving of physical models. Here, we introduced the concept of Physical Activation Functions (PAFs). This concept offers that instead of using general activation functions (AFs) such as ReLU, tanh, and sigmoid for all the neurons, one can use generic AFs that their mathematical expression is inherited from the physical laws of the investigating phenomena. The formula of PAFs may be inspired by the terms in the analytical solution of the problem. We showed that the PAFs can be inspired by any mathematical formula related to the investigating phenomena such as the initial or boundary conditions of the PDE system. We validated the advantages of PAFs for several PDEs including the harmonic oscillations, Burgers, Advection-Convection equation, and the heterogeneous diffusion equations. The main advantage of PAFs was in the more efficient constraining and interleaving of PINNs with the investigating physical phenomena and their underlying mathematical models. This added constraint significantly improved the predictions of PINNs for the testing data that was out-of-training distribution. Furthermore, the application of PAFs reduced the size of the PINNs up to 75% in different cases. Also, the value of loss terms was reduced by 1 to 2 orders of magnitude in some cases which is noteworthy for upgrading the training of the PINNs. The iterations required for finding the optimum values were also significantly reduced. It is concluded that using the PAFs helps in generating PINNs with less complexity and much more validity for longer ranges of prediction.

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。

↑