• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Low Power Electronics >X-DNNs: Systematic Cross-Layer Approximations for Energy-Efficient Deep Neural Networks
【24h】

X-DNNs: Systematic Cross-Layer Approximations for Energy-Efficient Deep Neural Networks

机译：X-DNN：节能深神经网络的系统交叉层近似

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

Growing interest towards the development of smart Cyber Physical Systems (CPS) and Internet of Things (IoT) has motivated the researchers to explore the suitability of carrying out embedded machine learning. This has enabled a new age of smart CPS and IoT with emerging applicationslike autonomous vehicles, smart cities and houses, advanced robotics, IoT-Healthcare, and Industry 4.0. Due to the availability of a huge amount of data and compute power, Deep Neural Networks (DNNs) have become one of the enabling technologies behind this current age of machine learning andintelligent systems. The benefits of DNNs however come at a high computational cost and require tremendous amount of energy/power resources that are typically not available on (embedded) IoT and CPS devices, especially when considering the IoT-Edge nodes. To improve the performance and energy/powerefficiency of these DNNs, this paper presents a cross-layer approximation methodology which exploits the error resiliency offered by DNNs at various hardware and software layers of the computing stack. We present various case studies at both software and hardware level in order to demonstratethe energy benefits of the proposed methodology. At software level we provide a systematic pruning methodology while at hardware level we provide a case study utilizing approximation of multipliers used for performing the weighted sum operation in the neural processing of DNNs.
机译：对智能网络物理系统（CPS）和物联网（IOT）的发展越来越兴趣，研究人员探讨了嵌入式机器学习的适用性。这使得智能CPS和IOT的新时代具有新兴应用程序，麦克风自主车辆，智能城市和房屋，高级机器人，物联网医疗保健和工业4.0。由于有大量数据和计算能力的可用性，深度神经网络（DNN）已成为当前机器学习和Intelligent系统时代的启用技术之一。然而，DNN的好处以高计算成本，并且需要大量的能量/功率资源，这些能量/功率资源通常不可用（嵌入式）物联网和CPS设备，特别是在考虑IoT边缘节点时。为了提高这些DNN的性能和能量/权力，本文提出了一种跨层近似方法，其利用DNN在计算堆栈的各种硬件和软件层中提供的误差弹性。我们在软件和硬件级别提出了各种案例研究，以规范所提出的方法的能量效益。在软件级别，我们提供系统修剪方法，而在硬件级别我们提供了利用用于在DNN的神经处理中执行加权和操作的乘法器近似的案例研究。

著录项

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