arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.10205cs.LGcs.NAmath.NAstat.ML
收藏

用神经网络求解泛函特征值问题

Solving the functional Eigen-Problem using Neural Networks

Tel Aviv University(特拉维夫大学)

Ido Ben-Shaul, Leah Bar, Nir Sochen

摘要:

在这项工作中,我们探讨的能力,神经网络(神经网络)作为一种工具,寻找特征对常微分方程。我们要解决的问题是,给定一个自伴算子,我们是否可以知道什么是本征函数,以及它们的匹配本征值。在图像处理中,求解特征问题的主题被广泛讨论,因为许多图像处理算法可以被认为是这样的算子。我们提出了一种替代数字方法找到本征对,这可能是更强大的,并有能力解决更复杂的问题。在这项工作中,我们专注于简单的问题,其中的解析解是已知的。这样,我们就能够在给定的设置中发现DNN(深度神经网络)的能力和缺点。

英文摘要:

In this work, we explore the ability of NN (Neural Networks) to serve as a tool for finding eigen-pairs of ordinary differential equations. The question we aime to address is whether, given a self-adjoint operator, we can learn what are the eigenfunctions, and their matching eigenvalues. The topic of solving the eigen-problem is widely discussed in Image Processing, as many image processing algorithms can be thought of as such operators. We suggest an alternative to numeric methods of finding eigenpairs, which may potentially be more robust and have the ability to solve more complex problems. In this work, we focus on simple problems for which the analytical solution is known. This way, we are able to make initial steps in discovering the capabilities and shortcomings of DNN (Deep Neural Networks) in the given setting.

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。

↑