Deep Learning for Autonomous Systems and Smart Cities

Almost everything we hear about Artificial Intelligence today is thanks to machine learning (ML) and especially ML algorithms following the end-to-end learning paradigm, which is commonly associated with a type of models referred to as Deep Learning. Deep learning has developed into a mature technology and it is nowadays an essential part in systems that require high-level perception capabilities, such as autonomous vehicles, robots that sense their environment, and multi-modal monitoring systems in smart cities. While successful solutions already exist for a number of research problems, the adoption of high-performing deep learning models in everyday life applications setting restrictions such as level of autonomy, computational power, and memory size, and real-time continuous operation, requires new advancements in both fundamental research and technology. Such research lies at the intersection of two H2020 Research and Innovation projects which jointly organize this summer school with prominent invited speakers and hands-on sessions on related tools and state-of-the-art technologies.