期刊
INTERNET OF THINGS: IOT INFRASTRUCTURES, IOT 360, PT II
卷 170, 期 -, 页码 484-492出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-319-47075-7_52
关键词
Deep neural networks; Distributed intelligence; Internet of things
类别
资金
- iMinds IoT research program
- Agency for Innovation by Science and Technology in Flanders (IWT)
Nowadays deep neural networks are widely used to accurately classify input data. An interesting application area is the Internet of Things (IoT), where a massive amount of sensor data has to be classified. The processing power of the cloud is attractive, however the variable latency imposes a major drawback in situations where near realtime classification is required. In order to exploit the apparent trade-off between utilizing the stable but limited embedded computing power of IoT devices and the seemingly unlimited computing power of Cloud computing at the cost of higher and variable latency, we propose a Big-Little architecture for deep neural networks. A small neural network trained to a subset of prioritized output classes is running on the embedded device, while a more specific classification is calculated when required by a large neural network in the cloud. We show the applicability of this concept in the IoT domain by evaluating our approach for state of the art neural network classification problems on popular embedded devices such as the Raspberry Pi and Intel Edison.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据