-
Can stable and accurate neural networks be computed? – On the barriers of deep learning and Smale's 18th problem
Deep learning (DL) has had unprecedented success and is now entering sci...
01/20/2021 ∙ by Vegard Antun, et al. ∙
20
∙
share
read it
-
On the infinite-dimensional QR algorithm
Spectral computations of infinite-dimensional operators are notoriously ...
11/16/2020 ∙ by Matthew J. Colbrook, et al. ∙
0
∙
share
read it
-
The troublesome kernel: why deep learning for inverse problems is typically unstable
There is overwhelming empirical evidence that Deep Learning (DL) leads t...
01/05/2020 ∙ by Nina M. Gottschling, et al. ∙
7
∙
share
read it
-
What do AI algorithms actually learn? - On false structures in deep learning
There are two big unsolved mathematical questions in artificial intellig...
06/04/2019 ∙ by Laura Thesing, et al. ∙
0
∙
share
read it
-
Uniform recovery in infinite-dimensional compressed sensing and applications to structured binary sampling
Infinite-dimensional compressed sensing deals with the recovery of analo...
04/30/2019 ∙ by Ben Adcock, et al. ∙
0
∙
share
read it
-
On instabilities of deep learning in image reconstruction - Does AI come at a cost?
Deep learning, due to its unprecedented success in tasks such as image c...
02/14/2019 ∙ by Vegard Antun, et al. ∙
14
∙
share
read it
