Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Vlacic, Verner"'
When utilized effectively, Supercloud heterogeneous systems have the potential to significantly enhance performance. Our ReDSEa tool-chain automates the mapping, load balancing, scheduling, parallelism, and overlapping processes for the Triangular Sy
Externí odkaz:
http://arxiv.org/abs/2305.19917
Linear and semidefinite programming (LP, SDP), regularisation through basis pursuit (BP) and Lasso have seen great success in mathematics, statistics, data science, computer-assisted proofs and learning. The success of LP is traditionally attributed
Externí odkaz:
http://arxiv.org/abs/2110.15734
The unprecedented success of deep learning (DL) makes it unchallenged when it comes to classification problems. However, it is well established that the current DL methodology produces universally unstable neural networks (NNs). The instability probl
Externí odkaz:
http://arxiv.org/abs/2109.06098
Autor:
Vlačić, Verner, Bölcskei, Helmut
We address the following question of neural network identifiability: Suppose we are given a function $f:\mathbb{R}^m\to\mathbb{R}^n$ and a nonlinearity $\rho$. Can we specify the architecture, weights, and biases of all feed-forward neural networks w
Externí odkaz:
http://arxiv.org/abs/2006.11727
Autor:
Vlačić, Verner, Bölcskei, Helmut
This paper addresses the following question of neural network identifiability: Does the input-output map realized by a feed-forward neural network with respect to a given nonlinearity uniquely specify the network architecture, weights, and biases? Ex
Externí odkaz:
http://arxiv.org/abs/1906.06994
We explore anisotropic regularisation methods in the spirit of [Holler & Kunisch, 14]. Based on ground truth data, we propose a bilevel optimisation strategy to compute the optimal regularisation parameters of such a model for the application of vide
Externí odkaz:
http://arxiv.org/abs/1602.01278
Autor:
Vlačić, Verner, Bölcskei, Helmut
Publikováno v:
In Advances in Mathematics 6 January 2021 376
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Vlacic, Verner
This thesis addresses two distinct problems in the theory of system identification by means of various novel techniques relying on complex analysis. Specifically, we study the analytic continuation of deep neural networks with meromorphic nonlinearit
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f9b633b43e60265fb71c3f6618266361
https://hdl.handle.net/20.500.11850/474903
https://hdl.handle.net/20.500.11850/474903