https://scholars.lib.ntu.edu.tw/handle/123456789/489214
標題: | Low Precision Deep Learning Training on Mobile Heterogeneous Platform | 作者: | Valery, O. Liu, P. PANGFENG LIU |
公開日期: | 2018 | 起(迄)頁: | 109-117 | 來源出版物: | Proceedings - 26th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, PDP 2018 | 摘要: | Recent advances in System-on-Chip architectures have made the use of deep learning suitable for a number of applications on mobile devices. Unfortunately, due to the computational cost of neural network training, it is often limited to inference task, e.g., prediction, on mobile devices. In this paper, we propose a deep learning framework that enables both deep learning training and inference tasks on mobile devices. While being able to accommodate with the heterogeneity of computing devices technology on mobile devices, it also uses OpenCL to efficiently leverage modern SoC capabilities, e.g., multi-core CPU, integrated GPU and shared memory architecture, and accelerate deep learning computation. In addition, our system encodes the arithmetic operations of deep networks down to 8-bit fixed-point on mobile devices. As a proof of concept, we trained three well-known neural networks on mobile devices and exhibited a significant performance gain, energy consumption reduction, and memory saving. © 2018 IEEE. |
URI: | https://scholars.lib.ntu.edu.tw/handle/123456789/489214 | DOI: | 10.1109/PDP2018.2018.00023 | SDG/關鍵字: | Energy utilization; Fixed point arithmetic; Memory architecture; Mobile computing; Network architecture; Neural networks; Program processors; Programmable logic controllers; System-on-chip; GPGPU; Heterogeneous platforms; Heterogeneous systems; Neural network training; Opencl; Shared memory architecture; System-on-chip architecture; Transfer learning; Deep learning |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。