Limitations of Deep Learning for Inverse Problems on Digital Hardware
MCML Authors
Gitta Kutyniok
Prof. Dr.
Principal Investigator
Abstract
Gitta Kutyniok
Prof. Dr.
Principal Investigator
Abstract
Deep neural networks have seen tremendous success over the last years. Since the training is performed on digital hardware, in this paper, we analyze what actually can be computed on current hardware platforms modeled as Turing machines, which would lead to inherent restrictions of deep learning. For this, we focus on the class of inverse problems, which, in particular, encompasses any task to reconstruct data from measurements. We prove that finite-dimensional inverse problems are not Banach-Mazur computable for small relaxation parameters. Even more, our results introduce a lower bound on the accuracy that can be obtained algorithmically.
article
IEEE Transactions on Information Theory
69.12. Dec. 2023.
Authors
H. Boche • A. Fono • G. KutyniokLinks
DOIResearch Area
BibTeXKey: BFK23