Limitations of deep learning for inverse problems on digital hardware

DOI10.1109/TIT.2023.3326879MaRDI QIDQ6575593zbMATH OpenFDO

Authors Holger Boche, Adalbert Fono, Gitta Kutyniok

Publication date 21 July 2024

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TIT.2023.3326879

zbMATH Keywords

current hardware platformsdeep neural networksTuring machines

Mathematics Subject Classification ID

Mathematical problems of computer architecture (68M07) Classical models of computation (Turing machines, etc.) (68Q04) Artificial neural networks and deep learning (68T07)

Cited in

(5)

• Compositional sparsity of learnable functions
• Inverse problems are solvable on real number signal processing hardware
• Computability of classification and deep learning: from theoretical limits to practical feasibility through quantization
• Mathematical algorithm design for deep learning under societal and judicial constraints: the algorithmic transparency requirement
• Modern and emerging phenomena in machine learning. Abstracts from the workshop held March 8--13, 2026

This page was built for publication: Limitations of deep learning for inverse problems on digital hardware

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6575593)