arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.19637math.NAcs.NA
收藏

哪些逆问题可以用神经网络求解?

What Inverse Problems Can Be Solved Using Neural Networks?

National Research Nuclear University MEPhI(国立核研究大学MEPhI);Lomonosov Moscow State University, Faculty of Physics(莫斯科罗蒙诺索夫国立大学物理系)

A. S. Leonov, D. V. Lukyanenko

AI总结:

本文明确神经网络仅能求解条件适定逆问题,因标准神经网络违反巴库欣斯基否决定理,提出基于神经网络的正则化算法(NNBRAs)求解不适定逆问题,其精度可与基础正则化方法相当。

摘要:

本文研究了求解逆问题的经典方法与神经网络方法之间的关系,回答了“哪些逆问题可以用神经网络求解”这一问题,结论是神经网络算法仅能求解条件适定问题(即吉洪诺夫意义下的适定问题)。原因在于,标准神经网络算法的设计违反了不适定问题理论中著名的巴库欣斯基否决定理,该定理指出,任何从理论上保证不适定问题稳定解的方法,必须显式依赖于数据的误差水平。本文强调了不适定问题理论中的正则化(RA)概念与神经网络训练中所理解的正则化之间的区别,后者违反了巴库欣斯基否决定理。由于这种违反,对神经网络架构、训练过程中的正则化或训练数据集进行任何扩充,都无法改变上述结论。本文从理论上证明,不适定逆问题仅能通过显式依赖于已知数据误差水平(作为参数)的参数化神经网络集合来求解。因此,作为标准神经网络算法的替代方案,本文提出了基于神经网络的正则化算法(NNBRAs)以求解不适定逆问题,其一种构建方法是使用正则化数据集,该数据集可通过特定的基础RA(显式依赖于数据误差水平)从受扰动的逆问题数据中生成。对最简单的有限维不适定逆问题的求解测试表明,NNBRA近似解的精度与基础RA的精度相当,而传统神经网络方法的误差可能无法接受。

英文摘要:

The relationship between classical methods for solving inverse problems and neural network methods is examined. An answer is provided to the question of what inverse problems can be solved using neural networks. The answer is that neural network algorithms can solve only conditionally well-posed problems (well-posed according to Tikhonov). The reason is that the design of standard neural network algorithms violates the well-known Bakushinsky veto from the theory of ill-posed problems. It requires that any method theoretically guaranteeing a stable solution to an ill-posed problem must depend explicitly on the error level of data. The article highlights the distinction between the concept of regularization (RA) in the theory of ill-posed problems and regularization as understood in neural network training, where Bakushinsky's veto is violated. Due to this violation, any changes to the neural network architecture, regularization during training, or training dataset augmentation cannot alter the answer specified above. It is theoretically demonstrated that an ill-posed inverse problem can be solved only by using a parametric set of neural networks that explicitly depend on the known error levels (as parameters) of data. Accordingly, as an alternative to standard neural network algorithms, \neural network based regularization algorithms (NNBRAs) are proposed to solve ill-posed inverse problems. One approach to their construction involves using a regularized dataset. Such a dataset can be generated from perturbed inverse-problem data using a specific base RA explicitly depended on the error level of the data. Test solving the simplest finite-dimensional ill-posed inverse problem demonstrate that the accuracy of the NNBRA approximate solutions is comparable to that of the base RA. At the same time, errors of conventional neural network methods may be unacceptable.

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。

↑