Limitations of Deep Learning for Inverse Problems on Digital Hardware

28 February 2022

Papers citing "Limitations of Deep Learning for Inverse Problems on Digital Hardware"

11 / 11 papers shown

Title
Deep-Unrolling Multidimensional Harmonic Retrieval Algorithms on Neuromorphic Hardware Vlad-Costin Andrei Alexandru P. Drăguţoiu Gabriel Béna Mahmoud Akl Yin Li Matthias Lohrmann U. Mönich Holger Boche 61 0 0 05 Dec 2024
Computability of Classification and Deep Learning: From Theoretical Limits to Practical Feasibility through Quantization Holger Boche Vít Fojtík Adalbert Fono Gitta Kutyniok 21 0 0 12 Aug 2024
Mathematical Algorithm Design for Deep Learning under Societal and Judicial Constraints: The Algorithmic Transparency Requirement Holger Boche Adalbert Fono Gitta Kutyniok FaML 23 4 0 18 Jan 2024
Reliable AI: Does the Next Generation Require Quantum Computing? Aras Bacho Holger Boche Gitta Kutyniok 9 2 0 03 Jul 2023
Computability of Optimizers Yunseok Lee Holger Boche Gitta Kutyniok 19 16 0 15 Jan 2023
Limitations of neural network training due to numerical instability of backpropagation Clemens Karner V. Kazeev P. Petersen 19 3 0 03 Oct 2022
Deep neural networks can stably solve high-dimensional, noisy, non-linear inverse problems Andrés Felipe Lerma Pineda P. Petersen 6 5 0 02 Jun 2022
NESTANets: Stable, accurate and efficient neural networks for analysis-sparse inverse problems Maksym Neyra-Nesterenko Ben Adcock 20 7 0 02 Mar 2022
A Rate-Distortion Framework for Explaining Black-box Model Decisions Stefan Kolek Duc Anh Nguyen Ron Levie Joan Bruna Gitta Kutyniok 14 14 0 12 Oct 2021
The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems N. Gottschling Vegard Antun A. Hansen Ben Adcock 6 28 0 05 Jan 2020
Learning to See in the Dark Cheng Chen Qifeng Chen Jia Xu V. Koltun 168 1,157 0 04 May 2018