• Publications
  • Influence
What do AI algorithms actually learn? - On false structures in deep learning
TLDR
There are two big unsolved mathematical questions in artificial intelligence (AI): (1) Why is deep learning so successful in classification problems and (2) why are neural nets based on deep learning at the same time universally unstable. Expand
  • 4
  • 1
  • PDF
PD and fuzzy logic control for earthquake resilient structures
TLDR
This research considers small‐scale and mathematical models of simple one‐story structures that are subjected to free and base‐motion excitations and installed with and without passive damping devices to gain an understanding of their dynamic behavior. Expand
  • 8
On the stable sampling rate for binary measurements and wavelet reconstruction
TLDR
We show that for binary measurements (modelled with Walsh functions and Hadamard matrices) and wavelet reconstruction the stable sampling rate is linear. Expand
  • 8
  • PDF
First principles study of vacancies and Al substitutional impurities in δ-TiN
The vacancies and aluminum substitutional impurities in the delta phase of titanium nitride have been studied through first principles spin polarized density functional theory calculations. FinalExpand
  • 8
Theoretical investigation on the stability and properties of a (10,0) BN-AlN nanotube junction.
The energetic, electronic and structural properties of a heterojunction formed by BN and AlN (10,0) nanotubes have been studied using first principles density functional theory. The differencesExpand
  • 19
Linear reconstructions and the analysis of the stable sampling rate
TLDR
The theory of sampling and the reconstruction of data has a wide range of applications and a rich collection of techniques. Expand
  • 5
  • PDF
Non-uniform Recovery Guarantees for Binary Measurements and Infinite-Dimensional Compressed Sensing
TLDR
We provide the first non-uniform recovery guarantees for infinite-dimensional compressed sensing with Walsh samples and wavelet reconstruction. Expand
  • 1
  • PDF
On reconstructions from measurements with binary functions
We consider the problem of reconstructions from linear measurements with binary functions. That is, the samples of the function are given by inner products with functions taking only the values 0 andExpand
  • 1
  • PDF
On Reconstructing Functions from Binary Measurements
We consider the problem of reconstructing a function from linear binary measurements. That is, the samples of the function are given by inner products with functions taking only the values 0 and 1.Expand
  • 1
The Oracle of DLphi
TLDR
We present a novel technique based on deep learning and set theory which yields exceptional classification and prediction results. Expand