Zobrazeno 1 - 10
of 67
pro vyhledávání: '"KAISHENG MA"'
Autor:
Linfeng Zhang, Kaisheng Ma
Publikováno v:
IEEE Transactions on Circuits and Systems for Video Technology. 33:2190-2201
Autor:
Tongda Wu, Kaisheng Ma, Jingtong Hu, Jason Xue, Jinyang Li, Xin Shi, Huazhong Yang, Yongpan Liu
Publikováno v:
IEEE Transactions on Circuits and Systems I: Regular Papers. 70:228-240
Autor:
Yanzhi Wang, Zhezhi He, Sia Huat Tan, Sheng Lin, Deliang Fan, Xiaolong Ma, Linfeng Zhang, Zhengang Li, Geng Yuan, Kaisheng Ma, Xuehai Qian, Xue Lin, Shaokai Ye
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:4930-4944
Large deep neural network (DNN) models pose the key challenge to energy efficiency due to the significantly higher energy consumption of off-chip DRAM accesses than arithmetic or SRAM operations. It motivates the intensive research on model compressi
Publikováno v:
2023 IEEE International Solid- State Circuits Conference (ISSCC).
Publikováno v:
2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA).
Autor:
Yinxiao Feng, Kaisheng Ma
Publikováno v:
Proceedings of the 59th ACM/IEEE Design Automation Conference.
Multi-chip integration is widely recognized as the extension of Moore's Law. Cost-saving is a frequently mentioned advantage, but previous works rarely present quantitative demonstrations on the cost superiority of multi-chip integration over monolit
Autor:
Yiming Chen, Guodong Yin, Zhanhong Tan, Mingyen Lee, Zekun Yang, Yongpan Liu, Huazhong Yang, Kaisheng Ma, Xueqing Li
Publikováno v:
Proceedings of the 59th ACM/IEEE Design Automation Conference.
Computing-in-memory (CiM) is a promising technique to achieve high energy efficiency in data-intensive matrix-vector multiplication (MVM) by relieving the memory bottleneck. Unfortunately, due to the limited SRAM capacity, existing SRAM-based CiM nee
Publikováno v:
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Autor:
Yukang Shi, Kaisheng Ma
Publikováno v:
2022 International Conference on Robotics and Automation (ICRA).
Collecting paired training data is difficult in practice, but the unpaired samples broadly exist. Current approaches aim at generating synthesized training data from unpaired samples by exploring the relationship between the corrupted and clean data.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e053061b5a860e4013c8ac4e2c29281
http://arxiv.org/abs/2204.10090
http://arxiv.org/abs/2204.10090