The collaborative research center SFB876 brings together data mining and embedded systems. On the one hand, embedded systems can be further improved using machine learning. On the other hand, data mining algorithms can be realized in hardware, e.g. FPGAs, or run on GPGPUs. The restrictions of ubiquitous systems in computing power, memory, and energy demand new algorithms for known learning tasks. These resource bounded learning algorithms may also be applied on extremely large data bases on servers.
1000 Participants, 54 Speakers and a Day Full of Innovation
The 5th Digital Future Science Match brought together AI experts from science, industry and politics to answer the question: What’s Next in Artificial Intelligence? Katharina Morik gave the keynote “AI and the sciences”.
more ...
The SFB876 is following with great interest the ongoing auction of frequencies for the new mobile radio standard 5G. In the course of the auction, the value of the limited available 5G spectrum will be measured. Currently, the bidders involved in the auction have already exceeded the 2 billion Euro limit.
The new mobile radio standard promises significantly increased transmission rates, ultra-reliable real-time communication (e.g. for autonomous driving and production environments) and maximum scalability to serve a massive number of small devices for the Internet of Things (IoT). In order to achieve these goals, the limited spectrum available must be utilized very efficiently. Using the latest methods of machine learning at all system levels, the SFB876 is also developing methods for increasing and ensuring scalability, energy efficiency, reliability and availability of 5G communication systems in subprojects A4 and B4.
For interested parties, the Communication Networks Institute, which is involved in both subprojects, continuously visualizes the round results of the current 5G auction:
https://www.kn.e-technik.tu-dortmund.de/cms/en/institute/News/2019/5G-Auktion/5G-Auction-Statistics/
The deep learning based software "PyTorch Geometric" from the projects A6 and B2 is a PyTorch based library for deep learning on irregular input data like graphs, point clouds or manifolds. In addition to general data structures and processing methods, the software contains a variety of recently published methods from the fields of relational learning and 3D computing.
Last Friday, the software attracted some attention via Twitter and Facebook when it was specifically shared and recommended by Yann LeCun. Since then, it has been collecting around 250 stars a day on GitHub and can be found in particular among the trending repositories at GitHub.
PyTorch Geometric (PyG) is freely available on GitHub at https://github.com/rusty1s/pytorch_geometric.
more ...
