Vegard Antun
Doctoral Research Fellow

Differential Equations and Computational Mathematics
Norwegian version of this page
Email
vegarant@math.uio.no
Mobile phone
+47 91553728
Room
1005
Username
Visiting address
Moltke Moes vei 35
Niels Henrik Abels hus
0851 OSLO
Postal address
Postboks 1053 Blindern
0316 OSLO
Other affiliations
Faculty of Mathematics and Natural Sciences
(Student)
Academic interests
Inverse problems, compressive sensing, wavelets, deep learning, neural networks.
For more information see my webpage
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]
 B. Adcock, V. Antun, A. C. Hansen, Uniform recovery in infinitedimensional compressed sensing and applications to structured binary sampling [arXiv]
 V. Antun, F. Renna, C. Poon, B. Adcock, A. C. Hansen, On instabilities of deep learning in image reconstruction  Does AI come at a cost? [arXiv]
Slides from selected talks
 How intelligent is artificial intelligence ?  On the surprising and mysterious secrets of deep learning (23. May 2019) link.
 A Practical Guide to Deep Learning at the Department of Mathematics (March 2019) slides, code.
 Trends in mathematics of information (16. May 2018) link.
Courses taught
 Autumn 2019: Lecturing MATINF 1100 – Modelling and computations
 Autumn 20161018: Plenary exercises in MATINF 1100 – Modelling and computations
 Spring 2017: Teaching assistant in MATINF 2360  Applications of linear algebra
Publications
 Antun, Vegard (2019). On Instabilities of Deep Learning in Image Reconstruction  Part I.
 Antun, Vegard (2019). On instabilities of deep learning in image reconstruction.
 Antun, Vegard (2019). On instabilities of deep learning in image reconstruction  Does AI come at a cost?.
 Antun, Vegard (2019). On instabilities of deep learning in image reconstruction  Does AI come at a cost?.
Published Aug. 22, 2016 4:24 PM
 Last modified Jan. 7, 2020 7:26 AM