• Program Highlights

    • FPGA machine learning

    • Deep learning

    • Probabilistic Graphical Models

    • Ultra Low Power Learning

    Small brains - Extending local computation resources

    While mobile devices like smartphones are becoming more and more powerful they are (still) limited by their available energy through battery size and density. Efficient computation of machine learning algorithms helps where data transfer to cloud facilities is not an option. One means is to use dedicated circuits for specific tasks.

    Learn how to locally leverage the power of machine learning with lectures about the usage of Field Programmable Gate Arrays for learning tasks. Especially for designing new algorithms, FPGAs provide a flexible and reconfigurable playground.

    More Info: Program Details | Registration Information | Student Grants

  • Program Highlights

    • FPGA machine learning

    • Deep learning

    • Probabilistic Graphical Models

    • Ultra Low Power Learning

    TU Dortmund University

    Located in the heart of the urban area around the river Ruhr, the TU Dortmund University has a long history in research. 40 years ago, the computer science faculty was founded as one of the first of its kind. Since then, the faculty has grown to more than 2.000 students originating from nearly 50 countries all over the world.

    The summer school takes place at the university's Seminar Building, Friedrich-Wöhler-Weg 6. Have a look at location to find more details.

    More Info: Program Details | Registration Information | Student Grants

  • Program Highlights

    • FPGA machine learning

    • Deep learning

    • Probabilistic Graphical Models

    • Ultra Low Power Learning

    Ultra low power learning

    A world full of sensors leads to two main developments: Gigantic centralized services, gathering and analyzing data, and highly distributed data generation. The latter demands respecting a multitude of restricted resources: Computational power, limited communication speed and reliablity, often limited energy. The PhyNodes are embedded computing and sensing platforms developed at the collaborative research center as a large scale testbed for the Internet of Things.

    Image: Wall of PhyNodes attached to transport containers.

    More Info: Program Details | Registration Information | Student Grants

  • Program Highlights

    • FPGA machine learning

    • Deep learning

    • Probabilistic Graphical Models

    • Ultra Low Power Learning

    Experimental logistics test lab

    The logistics lab (building in progress) provides the environment for testing complex transport scenarios. An indoor position system will enable accurate tracking of parcels, while movable racks allow sorting and testing of article flows. For the summer school, the lab provides the test facility to deploy trained location prediction models on embedded PhyNodes. This enables you to ultimately test your developments in realistic environments.

    Image: 3D model of the planned test building.

    More Info: Program Details | Registration Information | Student Grants