咨询与建议

限定检索结果

文献类型

  • 1 篇 期刊文献
  • 1 篇 会议

馆藏范围

  • 2 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 2 篇 工学
    • 2 篇 电气工程
  • 1 篇 理学
    • 1 篇 物理学

主题

  • 2 篇 analog approxima...
  • 1 篇 shape-based anal...
  • 1 篇 memory dac
  • 1 篇 task analysis
  • 1 篇 transistors
  • 1 篇 in-memory comput...
  • 1 篇 relu
  • 1 篇 current-domain
  • 1 篇 machine learning
  • 1 篇 neural network
  • 1 篇 analog multiplie...
  • 1 篇 schottky diodes
  • 1 篇 shape
  • 1 篇 circuits and sys...
  • 1 篇 training
  • 1 篇 generalized marg...

机构

  • 1 篇 washington univ ...
  • 1 篇 indian inst sci ...
  • 1 篇 univ toronto ele...

作者

  • 1 篇 chakrabartty sha...
  • 1 篇 tang tianwen
  • 1 篇 kumar pratik
  • 1 篇 thakur chetan si...
  • 1 篇 liscidini antoni...
  • 1 篇 nandi ankita

语言

  • 2 篇 英文
检索条件"主题词=Analog approximate computing"
2 条 记 录,以下是1-10 订阅
排序:
Bias-Scalable Near-Memory CMOS analog Processor for Machine Learning
收藏 引用
IEEE JOURNAL ON EMERGING AND SELECTED TOPICS IN CIRCUITS AND SYSTEMS 2023年 第1期13卷 312-322页
作者: Kumar, Pratik Nandi, Ankita Chakrabartty, Shantanu Thakur, Chetan Singh Indian Inst Sci Dept Elect Syst Engn NeuRon Lab Bengaluru 560012 India Washington Univ St Louis Dept Elect & Syst Engn St Louis MO 63130 USA
Bias-scalable analog computing is attractive for implementing machine learning (ML) processors with distinct power-performance specifications. For instance, ML implementations for server workloads are focused on highe... 详细信息
来源: 评论
A 22nm 56TOPS/W 6/8-bit Linearly-scalable R-2R Multiply-and-Accumulate Architecture with 2.2ns Latency  49
A 22nm 56TOPS/W 6/8-bit Linearly-scalable R-2R Multiply-and-...
收藏 引用
IEEE 49th European Solid-State Circuits Conference (ESSCIRC)
作者: Tang, Tianwen Liscidini, Antonio Univ Toronto Elect & Comp Engn Toronto ON Canada
This paper presents a current-domain compute-in-memory (CIM) architecture for acceleration of Artificial Intelligence (AI) edge inferencing. A novel multiply-and-accumulate (MAC) scheme is introduced by exploiting the... 详细信息
来源: 评论