Mobiprox: Supporting Dynamic Approximate Computing on Mobiles
원문 초록
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 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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SEZ-HARN: Self-Explainable Zero-shot Human Activity Recognition Network
Through-the-Wall Radar Human Activity Recognition WITHOUT Using Neural Networks
Enhancing Wearable Tap Water Audio Detection through Subclass Annotation in the HD-Epic Dataset
DeepConvContext: A Multi-Scale Approach to Timeseries Classification in Human Activity Recognition
Label Leakage in Federated Inertial-based Human Activity Recognition
MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices
토론
이 논문과 연결된 포럼 글이 아직 없습니다.