Search

Your search keyword '"Moser, Bernhard"' showing total 2,689 results
Start Over Author "Moser, Bernhard"
2,689 results on '"Moser, Bernhard"'

51. On the Discrepancy Normed Space of Event Sequences for Threshold-based Sampling

Author

Moser, Bernhard A.

Subjects
Mathematics - Metric Geometry, Electrical Engineering and Systems Science - Signal Processing, 46Exx, 54C35, 26B39, 26A45, 46B20, 94Axx
Abstract

Recalling recent results on the characterization of threshold-based sampling as quasi-isometric mapping, mathematical implications on the metric and topological structure of the space of event sequences are derived. In this context, the space of event sequences is extended to a normed space equipped with Hermann Weyl's discrepancy measure. Sequences of finite discrepancy norm are characterized by a Jordan decomposition property. Its dual norm turns out to be the norm of total variation. As a by-product a measure for the lack of monotonicity of sequences is obtained. A further result refers to an inequality between the discrepancy norm and total variation which resembles Heisenberg's uncertainty relation.

Published
2018

52. Variational Optimization of Informational Privacy

Author

Kumar, Mohit, Brunner, David, Moser, Bernhard A., Freudenthaler, Bernhard, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Prates, Raquel Oliveira, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Kotsis, Gabriele, editor, Tjoa, A Min, editor, Khalil, Ismail, editor, Fischer, Lukas, editor, Moser, Bernhard, editor, Mashkoor, Atif, editor, Sametinger, Johannes, editor, Fensel, Anna, editor, and Martinez-Gil, Jorge, editor

Published
2020
Full Text
View/download PDF

58. Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment

Author

Zellinger, Werner, Moser, Bernhard A., Grubinger, Thomas, Lughofer, Edwin, Natschläger, Thomas, and Saminger-Platz, Susanne

Subjects
Statistics - Machine Learning, Computer Science - Machine Learning
Abstract

A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations by means of maximizing the similarity between domain-specific activation distributions. The proposed metric results from modifying an integral probability metric such that it becomes less translation-sensitive on a polynomial function space. The metric has an intuitive interpretation in the dual space as the sum of differences of higher order central moments of the corresponding activation distributions. Under appropriate assumptions on the input distributions, error minimization is proven for the continuous case. As demonstrated by an analysis of standard benchmark experiments for sentiment analysis, object recognition and digit recognition, the outlined approach is robust regarding parameter changes and achieves higher classification accuracies than comparable approaches. The source code is available at https://github.com/wzell/mann., Comment: Preliminary version of this work appeared in ICLR

Published
2017
Full Text
View/download PDF

59. Deriving an Optimal Noise Adding Mechanism for Privacy-Preserving Machine Learning

Author

Kumar, Mohit, Rossbory, Michael, Moser, Bernhard A., Freudenthaler, Bernhard, Barbosa, Simone Diniz Junqueira, Editorial Board Member, Filipe, Joaquim, Editorial Board Member, Ghosh, Ashish, Editorial Board Member, Kotenko, Igor, Editorial Board Member, Zhou, Lizhu, Editorial Board Member, Yuan, Junsong, Founding Editor, Anderst-Kotsis, Gabriele, editor, Tjoa, A Min, editor, Khalil, Ismail, editor, Elloumi, Mourad, editor, Mashkoor, Atif, editor, Sametinger, Johannes, editor, Larrucea, Xabier, editor, Fensel, Anna, editor, Martinez-Gil, Jorge, editor, Moser, Bernhard, editor, Seifert, Christin, editor, Stein, Benno, editor, and Granitzer, Michael, editor

Published
2019
Full Text
View/download PDF

60. IL-21 conditions antigen-presenting human γδ T-cells to promote IL-10 expression in naïve and memory CD4+ T-cells

Author

Tyler, Christopher J, primary, Hoti, Inva, additional, Griffiths, Daniel D, additional, Cuff, Simone M, additional, Andrews, Robert, additional, Keisker, Maximilian, additional, Ahmed, Raya, additional, Hansen, Hinrich P, additional, Lindsay, James O, additional, Stagg, Andrew J, additional, Moser, Bernhard, additional, McCarthy, Neil E, additional, and Eberl, Matthias, additional

Published
2024
Full Text
View/download PDF

61. Conventional and unconventional T-cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients

Author

Burton, Ross J, primary, Raffray, Loïc, additional, Moet, Linda M, additional, Cuff, Simone M, additional, White, Daniel A, additional, Baker, Sarah E, additional, Moser, Bernhard, additional, O’Donnell, Valerie B, additional, Ghazal, Peter, additional, Morgan, Matt P, additional, Artemiou, Andreas, additional, and Eberl, Matthias, additional

Published
2024
Full Text
View/download PDF

62. Applying AI in Practice: Key Challenges and Lessons Learned

Author

Fischer, Lukas, Ehrlinger, Lisa, Geist, Verena, Ramler, Rudolf, Sobieczky, Florian, Zellinger, Werner, Moser, Bernhard, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Holzinger, Andreas, editor, Kieseberg, Peter, editor, Tjoa, A Min, editor, and Weippl, Edgar, editor

Published
2020
Full Text
View/download PDF

68. Donor ventilation parameters as predictors for length of mechanical ventilation after lung transplantation: Results of a prospective multicenter study

Author

Benazzo, Alberto, Schwarz, Stefan, Frommlet, Florian, Sinn, Katharina, Schweiger, Thomas, Klikovits, Thomas, Hoda, Alireza Mir, Moser, Bernhard, Matilla, Jose Ramon, Renyi Vamos, Ferenc, Lang, György, Jaksch, Peter, Di Nardo, Matteo, Del Sorbo, Lorenzo, Taghavi, Shahrokh, Keshavjee, Shaf, Klepetko, Walter, Cypel, Marcelo, and Hoetzenecker, Konrad

Published
2021
Full Text
View/download PDF

75. Ikk2-mediated inflammatory activation of arterial endothelial cells promotes the development and progression of atherosclerosis

Author

Mussbacher, Marion, Salzmann, Manuel, Haigl, Barbara, Basílio, José, Hochreiter, Bernhard, Gleitsmann, Viola, Moser, Bernhard, Hoesel, Bastian, Suur, Bianca E., Puhm, Florian, Ungerböck, Caroline, Kuttke, Mario, Forteza, Maria J., Binder, Christoph J., Ketelhuth, Daniel F.J., Assinger, Alice, and Schmid, Johannes A.

Published
2020
Full Text
View/download PDF

77. The Proteome of Extracellular Vesicles Released from Pulmonary Microvascular Endothelium Reveals Impact of Oxygen Conditions on Biotrauma

Author

Schaubmayr, Wolfgang, primary, Hochreiter, Beatrix, additional, Hunyadi-Gulyas, Eva, additional, Riegler, Louise, additional, Schmidt, Katy, additional, Tiboldi, Akos, additional, Moser, Bernhard, additional, Klein, Klaus U., additional, Krenn, Katharina, additional, Scharbert, Gisela, additional, Mohr, Thomas, additional, Schmid, Johannes A., additional, Spittler, Andreas, additional, and Tretter, Verena, additional

Published
2024
Full Text
View/download PDF

85. Conventional and unconventional T cell responses contribute to the prediction of clinical outcome and causative bacterial pathogen in sepsis patients

Author

Burton, Ross J., primary, Raffray, Loïc, additional, Moet, Linda M., additional, Cuff, Simone M., additional, White, Daniel A., additional, Baker, Sarah E., additional, Moser, Bernhard, additional, O’Donnell, Valerie B., additional, Ghazal, Peter, additional, Morgan, Matt P., additional, Artemiou, Andreas, additional, and Eberl, Matthias, additional

Published
2023
Full Text
View/download PDF

93. A role for miR-132 in learned safety

Author

Ronovsky, Marianne, Zambon, Alice, Cicvaric, Ana, Boehm, Vincent, Hoesel, Bastian, Moser, Bernhard A., Yang, Jiaye, Schmid, Johannes A., Haubensak, Wulf E., Monje, Francisco J., and Pollak, Daniela D.

Published
2019
Full Text
View/download PDF

94. On Mitigating the Utility-Loss in Differentially Private Learning: A New Perspective by a Geometrically Inspired Kernel Approach.

Author

Kumar, Mohit, Moser, Bernhard A., and Fischer, Lukas

Subjects
MACHINE learning, PRIVACY, MEDICAL sciences, DATA analysis, ACCURACY
Abstract

Privacy-utility tradeoff remains as one of the fundamental issues of differentially private machine learning. This paper introduces a geometrically inspired kernel-based approach to mitigate the accuracy-loss issue in classification. In this approach, a representation of the affine hull of given data points is learned in Reproducing Kernel Hilbert Spaces (RKHS). This leads to a novel distance measure that hides privacy-sensitive information about individual data points and improves the privacy-utility tradeoff via significantly reducing the risk of membership inference attacks. The effectiveness of the approach is demonstrated through experiments on MNIST dataset, Freiburg groceries dataset, and a real biomedical dataset. It is verified that the approach remains computationally practical. The application of the approach to federated learning is considered and it is observed that the accuracy-loss due to data being distributed is either marginal or not significantly high. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

98. Traffic of T lymphocytes

Author

Mackay, Charles R., Moser, Bernhard, Parnham, Michael J., editor, Moser, Bernhard, editor, Letts, Gordon L., editor, and Neote, Kuldeep, editor

Published
2006
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results