We study the problem of reconstructing solutions of inverse problems when only noisy measurements are available. We assume that the problem can be modeled with an infinite-dimensional forward operator that is not continuously invertible. Then, we restrict this forward operator to finite-dimensional spaces so that the inverse is Lipschitz continuous. For the inverse operator, we demonstrate that there exists a neural network which is a robust-to-noise approximation of the operator. In addition, we show that these neural networks can be learned from appropriately perturbed training data. We demonstrate the admissibility of this approach to a wide range of inverse problems of practical interest. Numerical examples are given that support the theoretical findings.
翻译:我们研究在只有噪音测量数据时,重建反向问题的解决办法的问题。 我们假设这个问题可以用一个无限的远方操作器来模拟,而远方操作器是不可不断倒置的。 然后, 我们把这个前方操作器限制在有限的维空间, 以便反之的是Lipschitz 的连续性。 对于反面操作器, 我们证明有一个神经网络, 是操作器的强大到噪音的近似。 此外, 我们还表明, 这些神经网络可以从适当扰动的培训数据中学习。 我们证明, 这种方法可以接受一系列广泛的反面的实际问题 。 我们给出了支持理论结论的数字例子 。