Embedded Deep-Learning (EDL)
Machine learning and in particular deep learning has dramatically improved the state-of-the-art in object detection, speech recognition, robotics, and many other domains. Whether it is superhuman performance in object recognition or beating human players in Go, the astonishing success of deep learning is achieved by deep neural networks trained with huge amounts of training examples and massive computing resources. Although already applied successfully in academic use-cases and several consumer products (e.g. machine translation), these data and computing requirements pose challenges for further market penetration. EDL will significantly improve the applicability of deep learning, by creating data efficient training methods, and tremendously improving computational efficiency, both for training and inference. This requires a comprehensive approach that combines the domains of machine learning and computer systems: both are strong in the Netherlands but hardly connected. EDL provides necessary innovations to improve efficiency in all areas, including simulated data, active learning, embedding model knowledge, visualization, platform mapping, low-power accelerators, data reduction, brain inspired spiking, and virtualization. EDL solutions are widely applicable. EDL provides the vital steps to enable deep learning in the roadmaps of Dutch and international companies involved in this proposal; its need is clearly visible from the tremendous industrial interest.
No project website available.