Search Results - "Moser, Bernhard A."

An Information Theoretic Approach to Privacy-Preserving Interpretable and Transferable Learning by Kumar, Mohit, Moser, Bernhard A, Fischer, Lukas, Freudenthaler, Bernhard

“…In order to develop machine learning and deep learning models that take into account the guidelines and principles of trustworthy AI, a novel information…”
Get full text

A Systematic Mapping Study of Predictive Maintenance in SMEs by Khan, Maqbool, Ahmad, Arshad, Sobieczky, Florian, Pichler, Mario, Moser, Bernhard A., Bukovsky, Ivo

“…The rapid growth of Industry 4.0 and predictive methods fostered a great potential for state-of-the-art techniques in the industrial sector, especially in…”
Get full text

Domain adaptation for regression under Beer–Lambert’s law by Nikzad-Langerodi, Ramin, Zellinger, Werner, Saminger-Platz, Susanne, Moser, Bernhard A.

“…We consider the problem of unsupervised domain adaptation (DA) in regression under the assumption of linear hypotheses (e.g. Beer–Lambert’s law) – a task…”
Get full text

On Quasi-Isometry of Threshold-Based Sampling by Moser, Bernhard A., Lunglmayr, Michael

“…The problem of isometry for threshold-based sampling such as integrate-and-fire or send-on-delta is addressed. While for uniform sampling the Parseval theorem…”
Get full text

On generalization in moment-based domain adaptation by Zellinger, Werner, Moser, Bernhard A., Saminger-Platz, Susanne

“…Domain adaptation algorithms are designed to minimize the misclassification risk of a discriminative model for a target domain with little training data by…”
Get full text

A Similarity Measure for Image and Volumetric Data Based on Hermann Weyl's Discrepancy by Moser, B. A.

“…The paper focuses on similarity measures for translationally misaligned image and volumetric patterns. For measures based on standard concepts such as…”
Get full text

On Stability of Distance Measures for Event Sequences Induced by Level-Crossing Sampling by Moser, Bernhard A., Natschlager, Thomas

“…While Shannon's paradigm of sampling is based on equidistant points in time, triggered by a clock, level-crossing sampling schemes are based on the evaluation…”
Get full text

A role for miR-132 in learned safety by Ronovsky, Marianne, Zambon, Alice, Cicvaric, Ana, Boehm, Vincent, Hoesel, Bastian, Moser, Bernhard A., Yang, Jiaye, Schmid, Johannes A., Haubensak, Wulf E., Monje, Francisco J., Pollak, Daniela D.

“…Learned safety is a fear inhibitory mechanism, which regulates fear responses, promotes episodes of safety and generates positive affective states. Despite its…”
Get full text

Geometric Characterization of Weyl’s Discrepancy Norm in Terms of Its n-Dimensional Unit Balls by Moser, Bernhard A.

“…Weyl’s discrepancy measure induces a norm on ℝ n which shows a monotonicity and a Lipschitz property when applied to differences of index-shifted sequences. It…”
Get full text

Managing human-AI collaborations within Industry 5.0 scenarios via knowledge graphs: key challenges and lessons learned by Krause, Franz, Paulheim, Heiko, Kiesling, Elmar, Kurniawan, Kabul, Leva, Maria Chiara, Estrada-Lugo, Hector Diego, Stübl, Gernot, Üre, Nazim Kemal, Dominguez-Ledo, Javier, Khan, Maqbool, Demolder, Pedro, Gaux, Hans, Heinzl, Bernhard, Hoch, Thomas, Martinez-Gil, Jorge, Silvina, Agastya, Moser, Bernhard A.

“…In this paper, we discuss technologies and approaches based on Knowledge Graphs (KGs) that enable the management of inline human interventions in AI-assisted…”
Get full text

Spiking neural networks in the Alexiewicz topology: A new perspective on analysis and error bounds by Moser, Bernhard A., Lunglmayr, Michael

“…In order to ease the analysis of error propagation in neuromorphic computing and to get a better understanding of spiking neural networks (SNN), we address the…”
Get full text

On the truncated Hausdorff moment problem under Sobolev regularity conditions by Zellinger, Werner, Moser, Bernhard A.

“…•We analyze the error of recovering regular probability density functions from its truncated sequence of moments.•We propose a new bound on the L1-distance…”
Get full text

On Mitigating the Utility-Loss in Differentially Private Learning: A New Perspective by a Geometrically Inspired Kernel Approach by Kumar, Mohit, Moser, Bernhard A., Fischer, Lukas

“…Privacy-utility tradeoff remains as one of the fundamental issues of differentially private machine learning. This paper introduces a geometrically inspired…”
Get full text

Robust unsupervised domain adaptation for neural networks via moment alignment by Zellinger, Werner, Moser, Bernhard A., Grubinger, Thomas, Lughofer, Edwin, Natschläger, Thomas, Saminger-Platz, Susanne

“…•A novel metric-based regularization for domain-invariant training of neural networks.•Some theoretical properties of the proposed moment-based metric are…”
Get full text

An optimal (∊,δ)-differentially private learning of distributed deep fuzzy models by Kumar, Mohit, Rossbory, Michael, Moser, Bernhard A., Freudenthaler, Bernhard

“…This study introduces a privacy-preserving framework for distributed deep fuzzy learning. Assuming training data as private, the problem of learning of local…”
Get full text

Stability of threshold-based sampling as metric problem by Moser, Bernhard A.

“…Threshold-based sampling schemes such send-on-delta, level-crossing with hysteresis and integrate-and-fire are studied as non-linear input-output systems that…”
Get full text

Matching event sequences approach based on Weyl's discrepancy norm by Moser, Bernhard A.

“…A novel approach for matching event sequences, that result from threshold-based sampling, is introduced. This approach relies on Hermann Weyl's discrepancy…”
Get full text

Rethinking data augmentation for adversarial robustness by Eghbal-zadeh, Hamid, Zellinger, Werner, Pintor, Maura, Grosse, Kathrin, Koutini, Khaled, Moser, Bernhard A., Biggio, Battista, Widmer, Gerhard

Get full text

On a regularization of unsupervised domain adaptation in RKHS by Gizewski, Elke R., Mayer, Lukas, Moser, Bernhard A., Nguyen, Duc Hoan, Pereverzyev, Sergiy, Pereverzyev, Sergei V., Shepeleva, Natalia, Zellinger, Werner

“…We analyze the use of the so-called general regularization scheme in the scenario of unsupervised domain adaptation under the covariate shift assumption…”
Get full text

The Range of a Simple Random Walk on $\mathbb{Z}$: An Elementary Combinatorial Approach by Moser, Bernhard A.

“…Two different elementary approaches for deriving an explicit formula for the distribution of the range of a simple random walk on $\mathbb{Z}$ of length $n$…”
Get full text