ORCID: https://orcid.org/0000-0002-8375-8946; Fono, Adalbert
ORCID: https://orcid.org/0000-0002-4302-8762 und Kutyniok, Gitta
ORCID: https://orcid.org/0000-0001-9738-2487
(2023):
Limitations of Deep Learning for Inverse Problems on Digital Hardware.
In: IEEE Transactions on Information Theory, Bd. 69, Nr. 12: S. 7887-7908
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.
Dokumententyp: | Zeitschriftenartikel |
---|---|
Keywords: | Computing theory,deep learning,signal processing,turing machine |
Fakultät: | Mathematik, Informatik und Statistik > Mathematik > Professur für Mathematische Grundlagen des Verständnisses der künstlichen Intelligenz |
Themengebiete: | 000 Informatik, Informationswissenschaft, allgemeine Werke > 000 Informatik, Wissen, Systeme |
ISSN: | 0018-9448 |
Sprache: | Englisch |
Dokumenten ID: | 126235 |
Datum der Veröffentlichung auf Open Access LMU: | 27. Mai 2025 06:44 |
Letzte Änderungen: | 27. Mai 2025 06:44 |