Zobrazeno 1 - 10
of 92
pro vyhledávání: '"Dähne, Sven"'
Autor:
Alber, Maximilian, Lapuschkin, Sebastian, Seegerer, Philipp, Hägele, Miriam, Schütt, Kristof T., Montavon, Grégoire, Samek, Wojciech, Müller, Klaus-Robert, Dähne, Sven, Kindermans, Pieter-Jan
In recent years, deep neural networks have revolutionized many application domains of machine learning and are key components of many critical decision or predictive processes. Therefore, it is crucial that domain specialists can understand and analy
Externí odkaz:
http://arxiv.org/abs/1808.04260
Autor:
Kindermans, Pieter-Jan, Hooker, Sara, Adebayo, Julius, Alber, Maximilian, Schütt, Kristof T., Dähne, Sven, Erhan, Dumitru, Kim, Been
Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing step ---add
Externí odkaz:
http://arxiv.org/abs/1711.00867
Autor:
Kindermans, Pieter-Jan, Schütt, Kristof T., Alber, Maximilian, Müller, Klaus-Robert, Erhan, Dumitru, Kim, Been, Dähne, Sven
DeConvNet, Guided BackProp, LRP, were invented to better understand deep neural networks. We show that these methods do not produce the theoretically correct explanation for a linear model. Yet they are used on multi-layer networks with millions of p
Externí odkaz:
http://arxiv.org/abs/1705.05598
Understanding neural networks is becoming increasingly important. Over the last few years different types of visualisation and explanation methods have been proposed. However, none of them explicitly considered the behaviour in the presence of noise
Externí odkaz:
http://arxiv.org/abs/1611.07270
Autor:
Schultze-Kraft, Matthias, Birman, Daniel, Rusconi, Marco, Allefeld, Carsten, Görgen, Kai, Dähne, Sven, Blankertz, Benjamin, Haynes, John-Dylan
Publikováno v:
Proceedings of the National Academy of Sciences of the United States of America, 2016 Jan . 113(4), 1080-1085.
Externí odkaz:
https://www.jstor.org/stable/26467537
Publikováno v:
In IFAC PapersOnLine 2015 48(20):447-452
Autor:
Haufe, Stefan, Meinecke, Frank, Görgen, Kai, Dähne, Sven, Haynes, John-Dylan, Blankertz, Benjamin, Bießmann, Felix
Publikováno v:
In NeuroImage 15 February 2014 87:96-110
Autor:
Schreuder, Martijn, Riccio, Angela, Risetti, Monica, Dähne, Sven, Ramsay, Andrew, Williamson, John, Mattia, Donatella, Tangermann, Michael
Publikováno v:
In Artificial Intelligence In Medicine October 2013 59(2):71-80
Publikováno v:
BMC Neuroscience, Vol 10, Iss Suppl 1, p P129 (2009)
Externí odkaz:
https://doaj.org/article/3c1a79a6cd5d4672920e9ae288d61e93
Multi-Variate EEG Analysis as a Novel Tool to Examine Brain Responses to Naturalistic Music Stimuli.
Autor:
Sturm, Irene1,2,3 irene.sturm@charite.de, Dähne, Sven2, Blankertz, Benjamin2,4, Curio, Gabriel1,3,4,5
Publikováno v:
PLoS ONE. 10/28/2015, Vol. 10 Issue 10, p1-30. 30p.