Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Geuchen, Paul"'
Empirical studies have widely demonstrated that neural networks are highly sensitive to small, adversarial perturbations of the input. The worst-case robustness against these so-called adversarial examples can be quantified by the Lipschitz constant
Externí odkaz:
http://arxiv.org/abs/2311.01356
We study the universality of complex-valued neural networks with bounded widths and arbitrary depths. Under mild assumptions, we give a full description of those activation functions $\varrho:\mathbb{C}\to \mathbb{C}$ that have the property that thei
Externí odkaz:
http://arxiv.org/abs/2305.16910
Autor:
Geuchen, Paul, Voigtlaender, Felix
Complex-valued neural networks (CVNNs) have recently shown promising empirical success, for instance for increasing the stability of recurrent neural networks and for improving the performance in tasks with complex-valued inputs, such as in MRI finge
Externí odkaz:
http://arxiv.org/abs/2303.16813
Autor:
Geuchen, Paul, Voigtlaender, Felix
We prove a quantitative result for the approximation of functions of regularity $C^k$ (in the sense of real variables) defined on the complex cube $\Omega_n := [-1,1]^n +i[-1,1]^n\subseteq \mathbb{C}^n$ using shallow complex-valued neural networks. P
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6aaed3f00caba4eec1352fed14f527c3