Sie sind hier


Dr. Yizheng Zhao

With the growing usage of ontologies in many knowledge-intensive sectors, not only has the number of available ontologies increased considerably, but increasingly they are blowing up in size and becoming more complex to manage. Moreover, modelling domain knowledge in the form of ontologies is labour-intensive work which is expensive from an implementation perspective. There is therefore a strong demand for technologies and automated tools for creating restricted views of ontologies so that existing ontologies can be reused to their full potential. Forgetting is a non-standard reasoning service that seeks to create restricted views of ontologies by eliminating some terms from the ontologies in such a way that all logical consequences are preserved up to the remaining terms.

17.01.2019 - 10:15 h
Sahar Vahdati

Research is becoming increasingly digital, interdisciplinary, and data-driven and affects different environments in addition to academia, such as industry, and government. Research output representation, publication, mining, analysis, and visualization are taken to a new level, driven by the increased use of Web standards and digital scholarly communication initiatives. The heterogeneity of scholarly artifacts and their metadata spread over different Web data sources poses a major challenge for researchers with regard to search, retrieval and exploration. In this talk, I present a vision towards an Open Research by community involvement towards creating and curating metadata about scholarly events and publications.

10.01.2019 - 10:15 h

In this talk i will present an ongoing work on improving hands-free interaction. This is an extension of the discussion we had during my last oberseminar. The aim of this work is to improve hands-free interaction for content on the web. We discuss the different types of navigation on the web and our approach in trying to solve the challenge associated with "hops of interaction". We present an early stage prototype which shows our implementation and discuss the future directions for improvement.

13.12.2018 - 10:15 h

In this talk I will present ongoing work on concept contraction in the description logic EL. The aim of this work is to model concept change (how does a concept change due to new input?) as a reformulation of the well known AGM contraction model. We discuss an explicit construction of a concept contraction operator, as well as a set of postulates for such an operator. We then present a representation theorem, which shows that these two definitions are equivalent.

06.12.2018 - 10:15 h
Jan Niklas Hombeck

Eines der größten Anwendungsbereiche in der heutigen Forschung über künstliche Intelligenz ist das Meistern komplexer Videospiele, da diese u.a. aufgrund ihrer Simulationskapazitäten eine gute Forschungsumgebung darbieten. Das Ziel dieses Forschungspraktikums ist es daher, möglichst erfolgreiche Agenten für das Echtzeitstrategiespiel StarCraft II zu entwickeln. DiePySC2-API von DeepMind dient als Grundlage für die Python-basierte Implementierung diverser Agenten, sowie zur Erforschung und Entwicklung verschiedener Ansätze; von statischen Agenten (auch über die Erweiterung der zu Grunde liegenden API), über Bereiche des maschinellen Lernens und anderen Ansätzen wie beispielsweise die Verwendung von Suchbäumen.

29.11.2018 - 10:15 h
Sergei Koltcov

Entropy models are widely used in various scientific fields, such as statistical physics, biology, economics, and machine learning. However, while the models developed in statistical physics have been mostly based on deformed entropies, including the entropies of Renyi, Tsallis, and Sharma-Mittal, machines learning has been mainly relying on Boltzmann-Gibbs-Shannon entropy. This type of entropy has been often used as one of regularizers of topic models (TM) or for their diagnosis. Topic modeling is a class of algorithms based on the procedure of restoring of a multidimensional distribution as a mixture of hidden distributions. One of the unsolved problems in TM is the choice of the number of distributions in the mixture. Another problem is its semantic stability.

26.11.2018 - 16:15 h

Convolutional neural networks (CNNs) have gain great success in many fields in machine learning. It is however not so obvious how convolution can be performed on non-Euclidean structures such as graphs. Starting from a simple diffusion model, we examine different concepts, namely, the graph Laplacian matrix and the Fourier transform, and show the relations between them. The convolution on graphs can be naturally defined once these relations become clear.

22.11.2018 - 10:15 h

Sensory data in sequential format can be obtained from different sensors describing different events. As a clear example of their usability, a smartphone has several inbuilt sensors such as accelerometer, gyroscope, magnetometer, etc. Independently, each sensor continuously measures an action value (e.g. acceleration) at each time stamp. However, the interpretation of a series of instantaneous actions to higher-level events is complicated due to the lack of information in the one-dimensional series and the high similarity among different events. Inspired from image processing, sensory words are new descriptors of sequential data, where it captures the magnitude and orientation of data points and present them in frequency histogram.

08.11.2018 - 10:15 h

The aim of the research project GazeMining by WeST and EYEVIDO GmbH is to capture Web sessions semantically and thus obtain a comprehensive yet rich picture of visual content as presented to the users, alongside attention and interaction by the users. This talk will provide you with the overall motivation, the current status and the future plans of the project.

18.10.2018 - 10:15 h

People widely use online social media to search for authorised information, disseminate and communication during breaking events such as natural disasters, political elections. On the other hand, along with verified information, it is also used to spread rumours which might cause undesirable circumstances. Therefore, early detection of emerging rumours is crucial task to deal with them, and challenging due to lack of sufficient information on circulating rumour.

11.10.2018 - 10:15 h