Vegard Antun

Academic interests

Inverse problems, compressive imaging, wavelets, deep learning, neural networks.

For more information see my webpage.

Publications

• V. Antun, M. J. Colbrook, A. C. Hansen. Proving Existence Is Not Enough: Mathematical Paradoxes Unravel the Limits of Neural Networks in Artificial Intelligence, SIAM News, 2022, 55 (4) 1-4.
• M. Colbrook, V. Antun, A. C. Hansen. The difficulty of computing stable and accurate neural networks: On the barriers of deep learning and Smale's 18th problem, Proc. Natl. Acad. Sci., USA, 2022, 119(12).
• V. Antun. Recovering wavelet coefficients from binary samples using fast transforms, (to appear in SIAM J. Sci. Comput.), [arXiv].
• V. Antun, Ø. Ryan. On the unification of schemes for and software wavelets on the interval. Acta Appl. Math., 2021. [Technical report]
• B. Adcock, V. Antun, A. C. Hansen. Uniform recovery in infinite-dimensional compressed sensing and applications to structured binary sampling. Appl. Comput. Harmon. Anal., 2021. (to appear) [arXiv].
• V. Antun, N. M. Gottschling, A. C. Hansen, B. Adcock. Deep Learning in Scientific Computing: Understanding the Instability Mystery. SIAM News, 2021.
• V. Antun, F. Renna, C. Poon, B. Adcock, A. C. Hansen. On instabilities of deep learning in image reconstruction and the potential costs of AI. Proc. Natl. Acad. Sci. USA, 2020. [arXiv]. In the news: [titan.uio.no], [datatech], [dagensmedisin], [Teknisk ukeblad] [digi], [Physics World], [Health Care Business], [Radiology Business], [The Register], [Science daily], [Psychology Today], [Government Computing], [Diagnostic Imaging], [News Medical], [Press Release Point], [Tech Xplore], [Aunt Minnie], [My Science], [Digit], [The Talking Machines], [Rama on Healthcare], [News8PLus], [Healthcare in Europe], [AuntminnieEurope], [AI Development Hub], [FirstWord MedTech], [AI daily], [Cam. Univ. News].
• R. V. Zicari, J. Brusseau, S. N. Blomberg • H. C. Christensen, M. Coffee, M. B. Ganapini, S. Gerke, T. K. Gilbert, E. Hickman, E. Hildt, S. Holm, U. Kühne, V. I. Madai, W. Osika, A. Spezzatti, E. Schnebel, J. J. Tithi, D. Vetter, M. Westerlund, R. Wurth. J. Amann, V. Antun, V. Beretta, F. Bruneault, E. Campano, B. Düdder, A. Gallucci, E. Goffi, C. B. Haase, T. Hagendorff, P. Kringen, F. Möslein, D. Ottenheimer, M. Ozols, L. Palazzani, M. Petrin, K. Tafur, J. Tørresen, H. Volland, G. Kararigas. On Assessing Trustworthy AI in Healthcare. Machine Learning as a Supportive Tool to Recognize Cardiac Arrest in Emergency Calls, Front. Hum. Dyn., 08 July 2021.

Preprints

• N. Gottschling, V. Antun, B. Adcock, A. C. Hansen. The troublesome kernel: why deep learning for inverse problems is typically unstable, [arXiv].
• L. Thesing, V. Antun, A. C. Hansen. What do AI algorithms actually learn? - On false structures in deep learning, [arXiv].

Refereed Conference Articles

• M. Colbrook, V. Antun, A. C. Hansen. On the existence of stable and accurate neural networks for image reconstruction, Signal Processing with Adaptive Sparse Structured
  Representations (SPARS), 2019, [PDF]. 

PhD Thesis

• V. Antun. Stability and accuracy in compressive sensing and deep learning [pdf]

Courses taught

• Spring 2021: Lecturing MIEVU4020 – Introduction to Deep Learning
• Autumn 2020: Teaching assistant in MAT3110 – Introduction to Numerical Analysis
• Autumn 2019: Lecturing MAT-INF 1100 – Modelling and computations
• Autumn 2016-1018: Plenary exercises in MAT-INF 1100 – Modelling and computations
• Spring 2017: Teaching assistant in MAT-INF 2360 - Applications of linear algebra