BriefGPT.xyz
Jun, 2017
MobiRNN: 移动 GPU 上高效运行的循环神经网络
MobiRNN: Efficient Recurrent Neural Network Execution on Mobile GPU
HTML
PDF
Qingqing Cao, Niranjan Balasubramanian, Aruna Balasubramanian
TL;DR
本文介绍MobiRNN优化框架，旨在解决移动设备上RNN模型的隐私和效率问题。实现了专门针对移动GPU的GPU卸载。通过运行RNN模型以进行活动识别的评估，结果表明使用MobiRNN明显降低了在手机上运行RNN模型的延迟。
Abstract
In this paper, we explore optimizations to run
recurrent neural network
(RNN) models locally on
mobile devices
. RNN models are widely used for Natural Language Processing, Machine Translation, and other tasks. Ho
→