中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共19条，第1-10条 帮助

已选(0)清除 条数/页：   排序方式：
Rethinking the Importance of Quantization Bias, Toward Full Low-Bit Training 期刊论文
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2022, 卷号: 31, 页码: 7006-7019
作者:  Liu, Chang;  Zhang, Xishan;  Zhang, Rui;  Li, Ling;  Zhou, Shiyi;  Huang, Di;  Li, Zhen;  Du, Zidong;  Liu, Shaoli;  Chen, Tianshi
收藏  |  浏览/下载：19/0  |  提交时间：2023/07/12
Neural network acceleration  low precision training  quantization  
A Decomposable Winograd Method for N-D Convolution Acceleration in Video Analysis 期刊论文
INTERNATIONAL JOURNAL OF COMPUTER VISION, 2021, 页码: 21
作者:  Huang, Di;  Zhang, Rui;  Zhang, Xishan;  Wu, Fan;  Wang, Xianzhuo;  Jin, Pengwei;  Liu, Shaoli;  Li, Ling;  Chen, Yunji
收藏  |  浏览/下载：45/0  |  提交时间：2021/12/01
Convolution neural networks  Model acceleration  Winograd algorithm  Video analysis  
ParaML: A Polyvalent Multicore Accelerator for Machine Learning 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2020, 卷号: 39, 期号: 9, 页码: 1764-1777
作者:  Zhou, Shengyuan;  Guo, Qi;  Du, Zidong;  Liu, Daofu;  Chen, Tianshi;  Li, Ling;  Liu, Shaoli;  Zhou, Jinhong;  Temam, Olivier;  Feng, Xiaobing;  Zhou, Xuehai;  Chen, Yunji
收藏  |  浏览/下载：60/0  |  提交时间：2020/12/10
Neural networks  Machine learning  Testing  Support vector machines  Linear regression  Computers  Computer architecture  Accelerator  machine learning (ML) techniques  multicore accelerator  
Addressing Irregularity in Sparse Neural Networks Through a Cooperative Software/Hardware Approach 期刊论文
IEEE TRANSACTIONS ON COMPUTERS, 2020, 卷号: 69, 期号: 7, 页码: 968-985
作者:  Zeng, Xi;  Zhi, Tian;  Zhou, Xuda;  Du, Zidong;  Guo, Qi;  Liu, Shaoli;  Wang, Bingrui;  Wen, Yuanbo;  Wang, Chao;  Zhou, Xuehai;  Li, Ling;  Chen, Tianshi;  Sun, Ninghui;  Chen, Yunji
收藏  |  浏览/下载：60/0  |  提交时间：2020/12/10
Accelerator  architecture  deep neural networks  sparsity  
Machine Learning Computers With Fractal von Neumann Architecture 期刊论文
IEEE TRANSACTIONS ON COMPUTERS, 2020, 卷号: 69, 期号: 7, 页码: 998-1014
作者:  Zhao, Yongwei;  Fan, Zhe;  Du, Zidong;  Zhi, Tian;  Li, Ling;  Guo, Qi;  Liu, Shaoli;  Xu, Zhiwei;  Chen, Tianshi;  Chen, Yunji
收藏  |  浏览/下载：62/0  |  提交时间：2020/12/10
Machine learning  Computers  Fractals  Programming  Computer architecture  Graphics processing units  Matrix decomposition  Machine learning  architecture  neural networks  programming efficiency  
Addressing Sparsity in Deep Neural Networks 期刊论文
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS, 2019, 卷号: 38, 期号: 10, 页码: 1858-1871
作者:  Zhou, Xuda;  Du, Zidong;  Zhang, Shijin;  Zhang, Lei;  Lan, Huiying;  Liu, Shaoli;  Li, Ling;  Guo, Qi;  Chen, Tianshi;  Chen, Yunji
收藏  |  浏览/下载：266/0  |  提交时间：2019/12/10
Accelerator  architecture  deep neural networks (DNNs)  sparsity  
An Instruction Set Architecture for Machine Learning 期刊论文
ACM TRANSACTIONS ON COMPUTER SYSTEMS, 2019, 卷号: 36, 期号: 3, 页码: 35
作者:  Chen, Yunji;  Lan, Huiying;  Du, Zidong;  Liu, Shaoli;  Tao, Jinhua;  Han, Dong;  Luo, Tao;  Guo, Qi;  Li, Ling;  Xie, Yuan;  Chen, Tianshi
收藏  |  浏览/下载：59/0  |  提交时间：2020/12/10
BSHIFT: A Low Cost Deep Neural Networks Accelerator 期刊论文
INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING, 2019, 卷号: 47, 期号: 3, 页码: 360-372
作者:  Yu, Yong;  Zhi, Tian;  Zhou, Xuda;  Liu, Shaoli;  Chen, Yunji;  Cheng, Shuyao
收藏  |  浏览/下载：92/0  |  提交时间：2019/08/16
Deep neural networks  Low power  Lossless  Accelerator  
Float-Fix: An Efficient and Hardware-Friendly Data Type for Deep Neural Network 期刊论文
INTERNATIONAL JOURNAL OF PARALLEL PROGRAMMING, 2019, 卷号: 47, 期号: 3, 页码: 345-359
作者:  Han, Dong;  Zhou, Shengyuan;  Zhi, Tian;  Wang, Yibo;  Liu, Shaoli
收藏  |  浏览/下载：81/0  |  提交时间：2019/08/16
Float-Fix  Neural network  Hardware accelerator  Data type  
Stealth-ACK: stealth transmissions of NoC acknowledgements 期刊论文
SCIENCE CHINA-INFORMATION SCIENCES, 2017, 卷号: 60, 期号: 9, 页码: 15
作者:  Tao, Jinhua;  Qiu, Shi;  Liu, Shaoli;  Chen, Tianshi;  Mao, Rui
收藏  |  浏览/下载：63/0  |  提交时间：2019/12/12
networks-on-chip  acknowledgement packet  router architecture  optimisation  routing algorithm