咨询与建议

限定检索结果

文献类型

  • 3 篇 期刊文献
  • 3 篇 会议

馆藏范围

  • 6 篇 电子文献
  • 0 种 纸本馆藏

日期分布

学科分类号

  • 6 篇 工学
    • 5 篇 电气工程
    • 4 篇 计算机科学与技术...
    • 1 篇 电子科学与技术(可...
    • 1 篇 信息与通信工程

主题

  • 6 篇 convolutional ne...
  • 2 篇 convolutional ne...
  • 1 篇 power demand
  • 1 篇 filters
  • 1 篇 medical signal d...
  • 1 篇 frequency 125.0 ...
  • 1 篇 registers
  • 1 篇 delays
  • 1 篇 computational ef...
  • 1 篇 neural nets
  • 1 篇 throughput
  • 1 篇 accelerator chip
  • 1 篇 data reuse
  • 1 篇 on-chip storage ...
  • 1 篇 left-to-right ar...
  • 1 篇 systolic arrays
  • 1 篇 four-lead electr...
  • 1 篇 arrays
  • 1 篇 convolution
  • 1 篇 random access me...

机构

  • 1 篇 univ chinese aca...
  • 1 篇 iranian res org ...
  • 1 篇 inha univ dept e...
  • 1 篇 univ regensburg ...
  • 1 篇 peking univ sch ...
  • 1 篇 peking univ mpw ...
  • 1 篇 chinese acad sci...
  • 1 篇 beijing acad art...
  • 1 篇 peking univ sch ...
  • 1 篇 chang gung mem h...
  • 1 篇 chang gung univ ...
  • 1 篇 beijing adv inno...
  • 1 篇 zhejiang univ co...
  • 1 篇 chosun univ coll...

作者

  • 1 篇 gorgin saeid
  • 1 篇 ibrahim muhammad...
  • 1 篇 wang chengxuan
  • 1 篇 usman muhammad
  • 1 篇 wang jiawei
  • 1 篇 li wanqian
  • 1 篇 li shuaiting
  • 1 篇 zhang yuanming
  • 1 篇 wang zongsheng
  • 1 篇 jeong min-wu
  • 1 篇 juan y.
  • 1 篇 dai zhenhui
  • 1 篇 shen haibin
  • 1 篇 wang yuan
  • 1 篇 cui xiaoxin
  • 1 篇 nisar malik zoha...
  • 1 篇 chen y. -h.
  • 1 篇 chen peiyu
  • 1 篇 zhong yi
  • 1 篇 zhao cheng

语言

  • 6 篇 英文
检索条件"主题词=convolutional neural network accelerator"
6 条 记 录,以下是1-10 订阅
排序:
Very-large-scale integration implementation of a convolutional neural network accelerator for abnormal heartbeat detection
收藏 引用
ELECTRONICS LETTERS 2020年 第7期56卷 330-+页
作者: Chen, Y. -H. Juan, Y. Chang Gung Univ Dept Elect Engn Taoyuan Taiwan Chang Gung Mem Hosp LinKou Inst Radiol Res Dept Radiat Oncol Taoyuan Taiwan
In this study, a very-large-scale integration implementation of a convolutional neural network (CNN) inference for abnormal heartbeat detection was proposed. Four-lead electrocardiogram signals were used to detect abn... 详细信息
来源: 评论
EWS: An Energy-Efficient CNN accelerator With Enhanced Weight Stationary Dataflow
收藏 引用
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS 2024年 第7期71卷 3478-3482页
作者: Wang, Chengxuan Wang, Zongsheng Li, Shuaiting Zhang, Yuanming Shen, Haibin Huang, Kejie Zhejiang Univ Coll Informat Sci & Elect Engn Hangzhou 310027 Peoples R China
In the realm of convolutional neural networks (CNNs), convolution operations exhibit a multiple degree of data reuse. However, the current Weight Stationary (WS) can't adequately exploit the potential local data r... 详细信息
来源: 评论
An Energy-Efficient Differential Frame convolutional accelerator with on-Chip Fusion Storage Architecture and Pixel-Level Pipeline Data Flow
An Energy-Efficient Differential Frame Convolutional Acceler...
收藏 引用
IEEE International Symposium on Circuits and Systems (ISCAS)
作者: Dai, Zhenhui Wang, Jiawei Zhong, Yi Feng, Kunyu Zhao, Cheng Jiang, Yuanyuan Chen, Peiyu Wang, Yuan Yu, Dunshan Cui, Xiaoxin Peking Univ Sch Integrated Circuits Beijing 100871 Peoples R China Peking Univ Sch Software & Microelect Beijing 102600 Peoples R China Peking Univ MPW Ctr Key Lab Microelect Devices & Circuits MoE Beijing 100871 Peoples R China Beijing Adv Innovat Ctr Integrated Circuits Beijing 100871 Peoples R China
convolutional neural networks require a huge amount of computation in video applications. For some specific tasks, such as surveillance, differential frame convolution reuses inter-frame data and significantly reduces... 详细信息
来源: 评论
Energy-Efficient In-SRAM Accumulation for CMOS-based CNN accelerators  22
Energy-Efficient In-SRAM Accumulation for CMOS-based CNN Acc...
收藏 引用
32nd Great Lakes Symposium on VLSI (GLSVLSI)
作者: Li, Wanqian Han, Yinhe Chen, Xiaoming Chinese Acad Sci Inst Comp Technol Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Beijing Acad Artificial Intelligence Beijing Peoples R China
State-of-the-art convolutional neural network (CNN) accelerators are typically communication-dominate architectures. To reduce the energy consumption of data accesses and also to maintain the high performance, researc... 详细信息
来源: 评论
Fusion for Tile-based Deconvolution Layers  18
Fusion for Tile-based Deconvolution Layers
收藏 引用
18th International SoC Design Conference (ISOCC)
作者: Jeong, Min-Wu Rhee, Chae Eun Inha Univ Dept Elect & Comp Engn Incheon South Korea
Recently, various deep learning accelerators are being studied through data flow structure improvement and memory access optimization. Among them, the encoder-decoder model is widely used in object detection and seman... 详细信息
来源: 评论
DSLR-CNN: Efficient CNN Acceleration Using Digit-Serial Left-to-Right Arithmetic
收藏 引用
IEEE ACCESS 2024年 12卷 174608-174622页
作者: Nisar, Malik Zohaib Ibrahim, Muhammad Sohail Gorgin, Saeid Usman, Muhammad Lee, Jeong-A Chosun Univ Coll IT Convergence Dept Comp Engn Gwangju 61452 South Korea Iranian Res Org Sci & Technol IROST Dept Elect Engn & Informat Technol Tehran 33535111 Iran Univ Regensburg Fac Informat & Data Sci D-93053 Regensburg Germany
Digit-serial arithmetic has emerged as a viable approach for designing hardware accelerators, reducing interconnections, area utilization, and power consumption. However, conventional methods suffer from performance a... 详细信息
来源: 评论