Johannes Kepler University of Linz

Convergence Results for Neural Networks via Electrodynamics

We study whether a depth two neural network can learn another depth two network using gradient descent. Assuming a linear output node, we show that the question of whether gradi...

An Iterative Regularization Method for Total Variation-Based Image Restoration

We introduce a new iterative regularization procedure for inverse problems based on the use of Bregman distances, with particular focus on problems arising in image processing. ...

Imaging of single molecule diffusion.

In recent years observations at the level of individual atoms and molecules became possible by microscopy and spectroscopy. Imaging of single fluorescence molecules has been ach...

Hybrid Solar Cells Based on Nanoparticles of CuInS₂ in Organic Matrices

Abstract We report on solution‐processed hybrid solar cells consisting of a nanocrystalline inorganic semiconductor, CuInS 2 , and organic materials. Synthesis of quantized CuIn...

Wigner-Seitz approach to spin splitting

A method is proposed that allows for a more precise evaluation of the spin splitting of electronic levels induced by the exchange interaction between effective-mass electrons an...

Future Data and Security Engineering