arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.11253math.NAcs.NAeess.IV
收藏

求解非线性反问题的数据一致性神经网络

Data-consistent neural networks for solving nonlinear inverse problems

Yoeri E. Boink, Markus Haltmeier, Sean Holman, Johannes Schwab

摘要:

数据辅助重建算法,结合训练的神经网络,是一种新的范式解决反问题。一种方法是首先应用经典的重建方法,然后应用神经网络来改进其解决方案。经验证据表明,这种两步方法提供了高质量的重建,但他们缺乏收敛性分析。在本文中,我们正式使用这样的两个步骤的方法与经典的正则化理论。我们提出了数据一致性神经网络,我们结合了经典的正则化方法。这就产生了一个数据驱动的正则化方法,我们提供了一个完整的收敛分析相对于噪声。数值模拟表明,与标准的两步深度学习方法相比,我们的方法在测试集的结构变化方面提供了更好的稳定性,同时在与训练集相似的测试数据上表现相似。我们的方法提供了一个稳定的解决方案的反问题,利用已知的非线性正演模型以及所需的解决方案流形的数据。

英文摘要:

Data assisted reconstruction algorithms, incorporating trained neural networks, are a novel paradigm for solving inverse problems. One approach is to first apply a classical reconstruction method and then apply a neural network to improve its solution. Empirical evidence shows that such two-step methods provide high-quality reconstructions, but they lack a convergence analysis. In this paper we formalize the use of such two-step approaches with classical regularization theory. We propose data-consistent neural networks that we combine with classical regularization methods. This yields a data-driven regularization method for which we provide a full convergence analysis with respect to noise. Numerical simulations show that compared to standard two-step deep learning methods, our approach provides better stability with respect to structural changes in the test set, while performing similarly on test data similar to the training set. Our method provides a stable solution of inverse problems that exploits both the known nonlinear forward model as well as the desired solution manifold from data.

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。

↑