Our work in Deep Learning is focused on Computer Vision with emphasis on object categorization, object-class segmentation, and action recognition tasks. Deep Learning methods produce a hierarchy of representations using multi-layered models, such as deep neural networks or deep graphical models. To accelerate calculations with GPUs, we make use of the Nvidia CUDA framework.
Projects:
University of Bonn, Institute for Computer Science, Departments: I, II, III, IV, V, VI Impress Data Privacy Statement ; NimbRo; Robotics