@inproceedings{ef7b331143fb4943bb94e8b0cd02fe23,
title = "FastDeepIoT: Towards understanding and optimizing neural network execution time on mobile and embedded devices",
abstract = "Deep neural networks show great potential as solutions to many sensing application problems, but their excessive resource demand slows down execution time, pausing a serious impediment to deployment on low-end devices. To address this challenge, recent literature focused on compressing neural network size to improve performance. We show that changing neural network size does not proportionally affect performance attributes of interest, such as execution time. Rather, extreme run-time nonlinearities exist over the network configuration space. Hence, we propose a novel framework, called FastDeepIoT, that uncovers the non-linear relation between neural network structure and execution time, then exploits that understanding to find network configurations that significantly improve the trade-off between execution time and accuracy on mobile and embedded devices. FastDeepIoT makes two key contributions. First, FastDeepIoT automatically learns an accurate and highly interpretable execution time model for deep neural networks on the target device. This is done without prior knowledge of either the hardware specifications or the detailed implementation of the used deep learning library.",
keywords = "Deep Learning, Execution Time, Internet of Things, Mobile Computing, Model Compression",
author = "Shuochao Yao and Yiran Zhao and Huajie Shao and Liu, {Sheng Zhong} and Dongxin Liu and Lu Su and Tarek Abdelzaher",
note = "Research reported in this paper was sponsored in part by NSF under grants CNS 16-18627 and CNS 13-20209 and in part by the Army Research Laboratory under Cooperative Agreements W911NF-09-2-0053 and W911NF-17-2-0196. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory, NSF, or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation here on.; 16th ACM Conference on Embedded Networked Sensor Systems, SENSYS 2018 ; Conference date: 04-11-2018 Through 07-11-2018",
year = "2018",
month = nov,
day = "4",
doi = "10.1145/3274783.3274840",
language = "English (US)",
series = "SenSys 2018 - Proceedings of the 16th Conference on Embedded Networked Sensor Systems",
publisher = "Association for Computing Machinery",
pages = "278--291",
booktitle = "SenSys 2018 - Proceedings of the 16th Conference on Embedded Networked Sensor Systems",
address = "United States",
}