On instabilities of deep learning in image reconstruction and the potential costs of AI V Antun, F Renna, C Poon, B Adcock, AC Hansen Proceedings of the National Academy of Sciences 117 (48), 30088-30095, 2020 | 670 | 2020 |
The difficulty of computing stable and accurate neural networks: On the barriers of deep learning and Smale’s 18th problem MJ Colbrook, V Antun, AC Hansen Proceedings of the National Academy of Sciences 119, 2022 | 133 | 2022 |
The troublesome kernel: why deep learning for inverse problems is typically unstable NM Gottschling, V Antun, B Adcock, AC Hansen arXiv preprint arXiv:2001.01258, 2020 | 105 | 2020 |
On assessing trustworthy AI in healthcare. Machine learning as a supportive tool to recognize cardiac arrest in emergency calls RV Zicari, J Brusseau, SN Blomberg, HC Christensen, M Coffee, ... Frontiers in Human Dynamics 3, 673104, 2021 | 30 | 2021 |
Uniform recovery in infinite-dimensional compressed sensing and applications to structured binary sampling B Adcock, V Antun, AC Hansen Applied and Computational Harmonic Analysis 55, 1-40, 2021 | 18 | 2021 |
The troublesome kernel--On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems NM Gottschling, V Antun, AC Hansen, B Adcock arXiv preprint arXiv:2001.01258, 2020 | 17 | 2020 |
Coherence estimates between hadamard matrices and daubechies wavelets V Antun University of Oslo, 2016 | 16 | 2016 |
What do AI algorithms actually learn?-On false structures in deep learning L Thesing, V Antun, AC Hansen arXiv preprint arXiv:1906.01478, 2019 | 11 | 2019 |
Proving existence is not enough: Mathematical paradoxes unravel the limits of neural networks in artificial intelligence V Antun, MJ Colbrook, AC Hansen Collections 55 (04), 2022 | 10 | 2022 |
Deep learning in scientific computing: Understanding the instability mystery V Antun, NM Gottschling, AC Hansen, B Adcock SIAM NEWS MARCH 2021, 8, 2021 | 7 | 2021 |
On instabilities of deep learning in image reconstruction—Does AI come at a cost? arXiv 2019 V Antun, F Renna, C Poon, B Adcock, AC Hansen arXiv preprint arXiv:1902.05300, 0 | 6 | |
Implicit regularization in AI meets generalized hardness of approximation in optimization--Sharp results for diagonal linear networks JS Wind, V Antun, AC Hansen arXiv preprint arXiv:2307.07410, 2023 | 4 | 2023 |
On the Unification of Schemes and Software for Wavelets on the Interval V Antun, Ø Ryan Acta Applicandae Mathematicae 173, 1-25, 2021 | 2 | 2021 |
Recovering wavelet coefficients from binary samples using fast transforms V Antun SIAM Journal on Scientific Computing 44 (3), A1315-A1336, 2022 | 1 | 2022 |
Stability and accuracy in compressive sensing and deep learning V Antun University of Oslo, 2020 | 1 | 2020 |
Uniform recovery guarantees for Hadamard sampling and wavelet reconstruction V Antun, B Adcock, A Hansen, Ø Ryan Signal Processing with Adaptive Sparse Structured Representations workshop …, 2017 | 1 | 2017 |
On the existence of stable and accurate neural networks for image reconstruction MJ Colbrook, V Antun, AC Hansen | 1 | 2009 |
On the existence of optimal multi-valued decoders and their accuracy bounds for undersampled inverse problems NM Gottschling, P Campodonico, V Antun, AC Hansen arXiv preprint arXiv:2311.16898, 2023 | | 2023 |
On accuracy and existence of approximate decoders for ill-posed inverse problems NM Gottschling, P Campodonico, V Antun, AC Hansen | | 2023 |
Mathematical paradoxes unearth the boundaries of AI M Colbrook, V Antun, A Hansen TheScienceBreaker 8 (3), 2022 | | 2022 |