20.500.12556/RUL-154705 Mobiprox supporting dynamic approximate computing on mobiles Runtime-tunable context-dependent network compression would make mobile deep learning (DL) adaptable to often varying resource availability, input “difficulty”, or user needs. The existing compression techniques significantly reduce the memory, processing, and energy tax of DL, yet, the resulting models tend to be permanently impaired, sacrificing the inference power for reduced resource usage. The existing tunable compression approaches, on the other hand, require expensive re-training, do not support arbitrary strategies for adapting the compression and do not provide mobile-ready implementations. In this paper we present Mobiprox, a framework enabling mobile DL with flexible precision. Mobiprox implements tunable approximations of tensor operations and enables runtime-adaptable approximation of the individual network layers. A profiler and a tuner included with Mobiprox identify the most promising neural network approximation configurations leading to the desired inference quality with the minimal use of resources. Furthermore, we develop control strategies that depending on contextual factors, such as the input data difficulty, dynamically adjust the approximation levels across a mobile DL model’s layers. We implement Mobiprox in Android OS and through experiments in diverse mobile domains, including human activity recognition and spoken keyword detection, demonstrate that it can save up to 15% system-wide energy with a minimal impact on the inference accuracy. approximate computing context-awareness mobile deep learning DL ubiquitous computing približno računanje kontekstno zavedanje mobilno globoko učenje vseprisotno računalništvo true false true Angleški jezik Slovenski jezik Članek v reviji 2024-02-23 11:35:55 2024-02-23 11:35:56 2024-12-12 03:54:57 0000-00-00 00:00:00 2024 0 0 Str. 16873-16886 no. 9 Vol. 11 2024 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004 2327-4662 10.1109/JIOT.2024.3365957 186557955 Mobiprox_Supporting_Dynamic_Approximate_Computing_on_Mobiles.pdf Mobiprox_Supporting_Dynamic_Approximate_Computing_on_Mobiles.pdf 1 00837C6E6869F5F5232CF6BC812A94CE 7ecb0a10b3638df77f43546db8d11a26ee30d55539d6581a7d44f3f16c6e933c 303784c4-b7bc-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=196902 https://ieeexplore.ieee.org/document/10436434 1 5321ca26-d237-11ee-9607-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=181237 Fakulteta za računalništvo in informatiko 0 0 0