Compiler-Level Approximate Mobile ComputingFabjančič, Matevž (Avtor) Pejović, Veljko (Mentor) Ubiquitous ComputingAdaptive ApproximationsApproximate ComputingCompilersAndroidDeep LearningWith the widespread use of smartphones, wearable devices and many applications of deep learning (DL), there is a growing interest in deploying DL on low-power devices. However, due to inferior computational resources and battery capacity limitations, this is a challenging task. One solution to this problem stems from approximate computing – by using approximations, we can sacrifice accuracy for better energy-efficiency. We develop an end-to-end system for adaptive approximate mobile computing (AMC), which enables transforming high-level definitions of convolutional neural networks into approximable DL models suitable for deployment within Android applications. We define ways of adaptively selecting among approximation levels to achieve better energy-efficiency of DL on smartphones while preserving the option of using non-approximated neural network variants. We evaluate the benefits of adaptive AMC on a concrete use case.20212021-11-05 13:35:00Magistrsko delo/naloga132867sl