arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2408.09143math.NAcs.LGcs.NA
收藏

基于奇异性增强神经网络的点源识别

Point Source Identification Using Singularity Enriched Neural Networks

The Chinese University of Hong Kong(香港中文大学);The Hong Kong Polytechnic University(香港理工大学)

Tianhao Hu, Bangti Jin, Zhi Zhou

AI总结:

针对点源识别逆问题因解的奇异性缺乏神经网络方法的问题,提出结合奇异性增强技术的神经网络算法,分别用基本解和神经网络表示奇异与正则部分,经严格误差分析与实验验证了有效性。

摘要:

点源反演这一逆问题是应用逆问题中的重要类别,但由于解本身具有固有奇异性,目前仍缺乏基于神经网络的点源识别方法。本研究提出一种识别点源的新算法,将神经网络与奇异性增强技术相结合:分别用基本解表示奇异部分、用神经网络表示正则部分,随后最小化包含未知点源的强度与位置、以及神经网络参数的经验损失。此外,研究将逆问题的条件稳定性论证与经验损失的泛化误差相结合,对该算法进行了严格的误差分析。通过多项具有挑战性的实验,验证了该方法的有效性。

英文摘要:

The inverse problem of recovering point sources represents an important class of applied inverse problems. However, there is still a lack of neural network-based methods for point source identification, mainly due to the inherent solution singularity. In this work, we develop a novel algorithm to identify point sources, utilizing a neural network combined with a singularity enrichment technique. We employ the fundamental solution and neural networks to represent the singular and regular parts, respectively, and then minimize an empirical loss involving the intensities and locations of the unknown point sources, as well as the parameters of the neural network. Moreover, by combining the conditional stability argument of the inverse problem with the generalization error of the empirical loss, we conduct a rigorous error analysis of the algorithm. We demonstrate the effectiveness of the method with several challenging experiments.

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。

↑