• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Soft Computing and Measurements >The research of degradation into the reliability of neural network computing systems made via use of nanoscale electronic elements
【24h】

The research of degradation into the reliability of neural network computing systems made via use of nanoscale electronic elements

机译：利用纳米级电子元件降低神经网络计算系统可靠性的研究

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

In this investigation the authors have conducted an experimental research into the information processing systems incorporated into up-to-date neural network computing devices. The research aims to study the computational processes running in such systems. The authors have addressed the issue of ensuring the target reliability indices of neural network computing systems built with the use of nanoscale electronic elements. Computational models of graphene-based field-effect nanoscale transistors have been designed. A computational model of the hardware implementation of artificial neural network built via use of this type of nanoscale transistors has been designed. The authors have also discovered a mechanism counteracting the system's reliability degradation by impacting the computational process.
机译：在这项调查中，作者对结合到最新神经网络计算设备中的信息处理系统进行了实验研究。该研究旨在研究在此类系统中运行的计算过程。作者已经解决了确保使用纳米级电子元件构建的神经网络计算系统的目标可靠性指标的问题。设计了基于石墨烯的场效应纳米级晶体管的计算模型。设计了通过使用这种类型的纳米级晶体管构建的人工神经网络的硬件实现的计算模型。作者还发现了一种通过影响计算过程来抵消系统可靠性下降的机制。

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