FWF - Deep Models - Resource-Efficient Deep Models for Embedded Systems

Deep representation learning is one of the main factors for the recent performance boost in many image, signal and speech processing problems. This is particularly true when having big amounts of data and almost unlimited computing resources available as demonstrated in competitions such as for example ImageNet. However, in real-world scenarios the computing infrastructure is often restricted and the computational requirements are not fulfilled. In this research project we suggest several directions for reducing the computational burden, i.e. the number of arithmetic operations, while maintaining the level of recognition performance. This enables to use deep models in mobile devices and embedded systems with limited power-consumption and computational resources.