...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Future generation computer systems >Multi-fidelity deep neural networks for adaptive inference in the internet of multimedia things
【24h】

Multi-fidelity deep neural networks for adaptive inference in the internet of multimedia things

机译：多媒体物联网中用于自适应推理的多保真深度神经网络

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Internet of Things (IoT) infrastructures are more and more relying on multimedia sensors to provide information about the environment. Deep neural networks (DNNs) could extract knowledge from this audiovisual data but they typically require large amounts of resources (processing power, memory and energy). If all limitations of the execution environment are known beforehand, we can design neural networks under these constraints. An IoT setting however is a very heterogeneous environment where the constraints can change rapidly. We propose a technique allowing us to deploy a variety of different networks at runtime, each with a specific complexity-accuracy trade-off but without having to store each network independently. We train a sequence of networks of increasing size and constrain each network to contain the parameters of all smaller networks in the sequence. We only need to store the largest network to be able to deploy each of the smaller networks. We experimentally validate our approach on different benchmark datasets for image recognition and conclude that we can build networks that support multiple trade-offs between accuracy and computational cost. (C) 2019 Elsevier B.V. All rights reserved.
机译：物联网（IoT）基础设施越来越依赖多媒体传感器来提供有关环境的信息。深度神经网络（DNN）可以从此视听数据中提取知识，但它们通常需要大量资源（处理能力，内存和能源）。如果事先知道执行环境的所有限制，我们可以在这些限制下设计神经网络。但是，物联网设置是一个非常异构的环境，约束条件可能会迅速变化。我们提出一种技术，使我们可以在运行时部署各种不同的网络，每个网络都有特定的复杂性-准确性折衷方案，而不必独立存储每个网络。我们训练一系列网络，这些网络的大小不断增加，并约束每个网络以包含该序列中所有较小网络的参数。我们只需要存储最大的网络即可部署每个较小的网络。我们通过实验验证了在不同基准数据集上进行图像识别的方法，并得出结论，我们可以构建支持在精度和计算成本之间进行多重权衡的网络。 （C）2019 Elsevier B.V.保留所有权利。

著录项

  • 来源
    《Future generation computer systems》 |2019年第8期|355-360|共6页
  • 作者

    Leroux Sam; Bohez Steven; De Coninck Elias; Van Molle Pieter; Vankeirsbilck Bert; Verbelen Tim; Simoens Pieter; Dhoedt Bart;

  • 作者单位

    Univ Ghent, IMEC, IDLab, Dept Informat Technol, iGent Tower,Technol Pk Zwijnaarde 15, B-9052 Ghent, Belgium;

    Univ Ghent, IMEC, IDLab, Dept Informat Technol, iGent Tower,Technol Pk Zwijnaarde 15, B-9052 Ghent, Belgium;

    Univ Ghent, IMEC, IDLab, Dept Informat Technol, iGent Tower,Technol Pk Zwijnaarde 15, B-9052 Ghent, Belgium;

    Univ Ghent, IMEC, IDLab, Dept Informat Technol, iGent Tower,Technol Pk Zwijnaarde 15, B-9052 Ghent, Belgium;

    Univ Ghent, IMEC, IDLab, Dept Informat Technol, iGent Tower,Technol Pk Zwijnaarde 15, B-9052 Ghent, Belgium;

    Univ Ghent, IMEC, IDLab, Dept Informat Technol, iGent Tower,Technol Pk Zwijnaarde 15, B-9052 Ghent, Belgium;

    Univ Ghent, IMEC, IDLab, Dept Informat Technol, iGent Tower,Technol Pk Zwijnaarde 15, B-9052 Ghent, Belgium;

    Univ Ghent, IMEC, IDLab, Dept Informat Technol, iGent Tower,Technol Pk Zwijnaarde 15, B-9052 Ghent, Belgium;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    IoT; Deep neural networks; Resource efficient inference;

    机译：物联网;深度神经网络;资源有效推理;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号