Zobrazeno 1 - 10
of 165
pro vyhledávání: '"Hinz, Peter"'
Autor:
Napp, Judith, Daeschlein, Georg, Napp, Matthias, von Podewils, Sebastian, Gümbel, Denis, Spitzmueller, Romy, Fornaciari, Paolo, Hinz, Peter, Jünger, Michael
Publikováno v:
GMS Hygiene and Infection Control, Vol 10, p Doc08 (2015)
Background: Cold atmospheric pressure plasma (CAP) with its many bioactive properties has defined a new medical field: the plasma medicine. However, in the related form of high-frequency therapy, CAP was even used briefly a century ago. The aim of th
Externí odkaz:
https://doaj.org/article/40859f5e63104053bbd12cedca7bf6a6
Autor:
Daeschlein, Georg, Reese, Kevin, Napp, Matthias, Spitzmueller, Romy, Hinz, Peter, Juenger, Michael, Kramer, Axel
Publikováno v:
GMS Hygiene and Infection Control, Vol 10, p Doc07 (2015)
Background and aims: Debridement therapy with sterile bred larvae in non-healing wounds is a widely accepted safe and efficient treatment modality. However, during application in the contaminated wound bed microbial contamination with potential micro
Externí odkaz:
https://doaj.org/article/d2c0ad8bba9047988a7eb0123b8c61ce
Autor:
Hinz, Peter
For fixed training data and network parameters in the other layers the L1 loss of a ReLU neural network as a function of the first layer's parameters is a piece-wise affine function. We use the Deep ReLU Simplex algorithm to iteratively minimize the
Externí odkaz:
http://arxiv.org/abs/2105.02831
Autor:
Hinz, Peter
Several current bounds on the maximal number of affine regions of a ReLU feed-forward neural network are special cases of the framework [1] which relies on layer-wise activation histogram bounds. We analyze and partially solve a problem in algebraic
Externí odkaz:
http://arxiv.org/abs/2103.17174
Autor:
Hinz, Peter, van de Geer, Sara
Feed-forward ReLU neural networks partition their input domain into finitely many "affine regions" of constant neuron activation pattern and affine behaviour. We analyze their mathematical structure and provide algorithmic primitives for an efficient
Externí odkaz:
http://arxiv.org/abs/2011.14895
Autor:
Alfke, Dominik, Baines, Weston, Blechschmidt, Jan, Sarmina, Mauricio J. del Razo, Drory, Amnon, Elbrächter, Dennis, Farchmin, Nando, Gambara, Matteo, Glas, Silke, Grohs, Philipp, Hinz, Peter, Kivaranovic, Danijel, Kümmerle, Christian, Kutyniok, Gitta, Lunz, Sebastian, Macdonald, Jan, Malthaner, Ryan, Naisat, Gregory, Neufeld, Ariel, Petersen, Philipp Christian, Reisenhofer, Rafael, Sheng, Jun-Da, Thesing, Laura, Trunschke, Philipp, von Lindheim, Johannes, Weber, David, Weber, Melanie
We present a novel technique based on deep learning and set theory which yields exceptional classification and prediction results. Having access to a sufficiently large amount of labelled training data, our methodology is capable of predicting the la
Externí odkaz:
http://arxiv.org/abs/1901.05744
Autor:
Hinz, Peter, van de Geer, Sara
We present a framework to derive upper bounds on the number of regions that feed-forward neural networks with ReLU activation functions are affine linear on. It is based on an inductive analysis that keeps track of the number of such regions per dime
Externí odkaz:
http://arxiv.org/abs/1806.01918
Autor:
Hinz, Peter
Bibliography: pages 110-115.
The performance analysis of parallel programs is a complex task, particularly if the program has to be efficient over a wide range of parallel machines. We have designed a performance analysis system called Chiron th
The performance analysis of parallel programs is a complex task, particularly if the program has to be efficient over a wide range of parallel machines. We have designed a performance analysis system called Chiron th
Externí odkaz:
http://hdl.handle.net/11427/16141