Search our Publications
Latest Publications
Jan Philip Goepfert, Barbara Hammer, Heiko Wersing , "Recovering Localized Adversarial Attacks", International Conference on Artificial Neural Networks ICANN, pp. 302-311, 2019.
AbstractClassification algorithms can achieve greatly improved per- formance when given the option to reject samples. In fact, knowing when the prediction for a given sample is too uncertain can provide valuable feedback to a system’s users. In order for users to better understand and judge a system’s capabilities, and be able to adequatly respond to rejected samples, we need to be able to explain why a given sample leads to a prediction with low c...
Download Bibtex file Per Mail Request
Heiko Wersing and Barbara Hammer , "Adversarial attacks hidden in plain sight", arXiv:1902.09286, 2019.
AbstractConvolutional neural networks have been used to achieve a string of successes dur- ing recent years, but their lack of interpretability remains a serious issue. Adversarial examples are designed to deliberately fool neural networks into making any desired incorrect classification, potentially with very high certainty. In this contribution, we underline the severity of the issue by presenting a technique that allows to hide such adversarial a...
Download Bibtex file Per Mail Request
Leonardo Novelli, Patricia Wollstadt, Pedro Mediano, Michael Wibral, Joseph Troy Lizier , "Large-scale directed network inference with multivariate transfer entropy and hierarchical statistical testing", Network Neuroscience, 2019.
AbstractNetwork inference algorithms are valuable tools for the study of large-scale neuroimaging datasets. Multivariate transfer entropy is a model-free measure that can capture nonlinear and lagged dependencies between time series to infer a minimal directed network model.Greedy algorithms have been proposed to efficiently deal with high-dimensional datasets,in a fashion that avoids redundant inferences and captures synergistic effects. Statistical tes...
Download Bibtex file
Sebastian Schmitt, Steffen Limmer, Nils Einecke, Viktor Losing, Sven Rebhan , "ESA Collision Avoidance Challenge", Kelvins - ESA's Advanced Concepts Competition Website, 2019.
AbstractToday, active collision avoidance among orbiting satellites has become a routine task in space operations, relying on validated, accurate and timely space surveillance data. For a typical satellite in Low Earth Orbit, hundreds of alerts are issued every week corresponding to possible close encounters between a satellite and another space object (in the form of conjunction data messages CDMs). After automatic processing and filtering, there remain...
Download Bibtex file Per Mail Request
Steffen Limmer and Tobias Rodemann , "Peak Load Reduction through Dynamic Pricing for Electric Vehicle Charging", International Journal of Electrical Power & Energy Systems, vol. 113, pp. 117 - 128, 2019.
AbstractTypically, peak demand charges account for a considerable part of the operating costs of public electric vehicle charging stations. An intelligent control of the charging processes can help to reduce the peak load and the corresponding fees. This can be additionally supported by the use of a dynamic pricing scheme, which encourages customers to provide as much flexibility as possible. The present work proposes a framework for the setting of dynam...
Download Bibtex file
Samuele Vinanzi, Christian Goerick, Angelo Cangelosi , "Mindreading for Robots: Predicting Intentions via Dynamical Clustering of Human Postures", 9th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, IEEE, 2019.
AbstractRecent advancements in robotics suggest a future where social robots will be deeply integrated in our society. In order to understand humans and engage in finer interactions, robots would greatly benefit from the ability of intention reading: the capacity to discern the high-level goal that is driving the low-level actions of an observed agent. This is particularly useful in joint action scenarios, where human and robot must collaborate to reach ...
Download Bibtex file
Satchit Ramnath, Payam Haghighi, Ji Hoon Kim, Duane Detwiler, Michael Berry, Jami J. Shah, Nikola Aulig, Patricia Wollstadt, Stefan Menzel , "Automatically Generating 60,000 CAD Variants for Big Data Applications", ASME 2019 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, 2019.
AbstractMachine leaning is opening up new ways of optimizing designs, but it requires large data sets for training and verification. While such data sets already exist for financial, sales and business applications, this is not the case for engineering products design data. This paper discusses our efforts in curating a large CAD data set with desired variety and validity for automotive body structural compositions. Manual creation of 60,000 CAD v...
Download Bibtex file
Tamas Bates, Jens Kober, Michael Gienger , "Multimodal Expressive Communication for Human-Robot Collaboration", Workshop on Expressivity for Sustained Human-Robot Interaction, 2019.
AbstractCollaboration between humans and robots presents a variety of difficult problems. In a practical sense, collaborative robots need to be safe to work with, capable of adapting to varied human behavior, and to react at human time scales. Additionally, however, for collaborative systems to really work they must also be able to communicate their needs, to express their intentions, and to understand communicative cues from their collaboration partners...
Download Bibtex file Per Mail Request
Christian Limberg, Heiko Wersing, Helge Ritter , "Active Learning for Image Recognition using a Visualization-Based User Interface", International Conference on Artificial Neural Networks, 2019.
AbstractThis paper introduces a novel approach for querying samples to be labeled in active learning for image recognition. By using dimension reduction techniques to create a 2D feature embedding for visualization, the user is able to efficiently label images for training a classifier. This is made possible by a querying strategy specifically designed for the visualization, seeking optimized bounding-box views for subsequent labeling. The approach is im...
Download Bibtex file
Akinobu Hayashi, Dirk Ruiken, Christian Goerick, Tadaaki Hasegawa , "Reasoning about Uncertain Parameters and Agent Behaviors through Encoded Experiences and Belief Planning", Artificial Intelligence, Special Issue on Autonomous Agents Modelling Other Agents, 2019.
AbstractRobots are expected to handle increasingly complex tasks. Such tasks often include interaction with novel objects or collaboration with unfamiliar agents. One of the key challenges for reasoning in such situations is the lack of accurate models that hinders the effectiveness of planners. We propose a system for online model adaptation that corrects hypothetical types and parameters of the models based on observations and encoded prior experiences...
Download Bibtex file
1 ... 79 80 81 82 83 84 ... 183
Follow us
