Sinc Kolmogorov-Arnold 网络及其在求解含奇异性偏微分方程中的应用
Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities
AI总结:
本文提出在 Kolmogorov-Arnold 网络中使用 Sinc 插值作为可学习激活函数,以有效逼近光滑函数和含奇异性的函数,并在物理信息神经网络求解偏微分方程中取得更好效果。
摘要:
在本文中,我们提出在 Kolmogorov-Arnold 网络(一种具有可学习激活函数的神经网络,最近作为多层感知机的替代方案受到关注)中使用 Sinc 插值。已有许多不同的函数表示被尝试,但我们表明 Sinc 插值提供了一种可行的替代方案,因为它在数值分析中已知能有效表示光滑函数和含奇异性的函数。这不仅对函数逼近重要,也对使用物理信息神经网络求解偏微分方程重要。通过一系列实验,我们表明 SincKANs 在我们考虑的大多数示例中提供了更好的结果。
英文摘要:
In this paper, we propose to use Sinc interpolation in the context of Kolmogorov-Arnold Networks, neural networks with learnable activation functions, which recently gained attention as alternatives to Multilayer Perceptron. Many different function representations have already been tried, but we show that Sinc interpolation proposes a viable alternative, since it is known in numerical analysis to effectively represent both smooth functions and functions with singularities. This is important not only for function approximation but also for solving the partial differential equations with physics-informed neural networks. Through a series of experiments, we show that SincKANs provide better results in almost all of the examples we have considered.
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。