Zobrazeno 1 - 10
of 1 555
pro vyhledávání: '"MA Xiaolong"'
Autor:
Zhao Guangxin, Chi Liqun, Liang Lin, Liu Jiaji, Ma Xiaolong, Zhang Yuxiao, Huang Qiuyue, Kong Qingyu
Publikováno v:
Journal of Cardiothoracic Surgery, Vol 19, Iss 1, Pp 1-9 (2024)
Abstract Background conventional coronary artery bypass grafting (CCABG) tends to cause severe complications in patients with comorbid Coronary Artery Diseases (CAD) and diabetes. On the other hand, the Minimally Invasive Cardiac Surgery Coronary Art
Externí odkaz:
https://doaj.org/article/07ad8a569805465cb89b18f1d54cb474
Autor:
Shen Dongfeng, Lv Xiaodong, Zhang Hui, Fei Chunyuan, Feng Jing, Zhou Jiaqi, Cao Linfeng, Ying Ying, Li Na, Ma Xiaolong
Publikováno v:
Polish Journal of Microbiology, Vol 73, Iss 1, Pp 59-68 (2024)
This study aimed to investigate the disparities between metagenomic next-generation sequencing (mNGS) and conventional culture results in patients with bronchiectasis. Additionally, we sought to investigate the correlation between the clinical charac
Externí odkaz:
https://doaj.org/article/31920f8831934e1d8c002b6e6353612f
Publikováno v:
Kongzhi Yu Xinxi Jishu, Iss 5, Pp 101-105 (2022)
Unmanned driving & remote driving transportation business in Xiwan Coal Mine requires three-dimensional coverage of wireless network with large bandwidth and low latency in light-load test area, heavy-load test area and whole mining area. In view of
Externí odkaz:
https://doaj.org/article/b675f673babb4c66a9b9f16f42786a6c
Mixture-of-Experts (MOE) has garnered significant attention for their ability to scale up neural networks while utilizing the same or even fewer active parameters. However, MoE does not relieve the massive memory requirements of networks, which limit
Externí odkaz:
http://arxiv.org/abs/2412.00069
Deep neural networks (DNNs) are frequently employed in a variety of computer vision applications. Nowadays, an emerging trend in the current video distribution system is to take advantage of DNN's overfitting properties to perform video resolution up
Externí odkaz:
http://arxiv.org/abs/2407.02813
Autor:
Ma, Xiaolong, Yan, Feng, Yang, Lei, Foster, Ian, Papka, Michael E., Liu, Zhengchun, Kettimuthu, Rajkumar
First-come first-serve scheduling can result in substantial (up to 10%) of transiently idle nodes on supercomputers. Recognizing that such unfilled nodes are well-suited for deep neural network (DNN) training, due to the flexible nature of DNN traini
Externí odkaz:
http://arxiv.org/abs/2404.15668
FlameFinder is a deep metric learning (DML) framework designed to accurately detect flames, even when obscured by smoke, using thermal images from firefighter drones during wildfire monitoring. Traditional RGB cameras struggle in such conditions, but
Externí odkaz:
http://arxiv.org/abs/2404.06653
Deep neural networks have demonstrated remarkable performance in various tasks. With a growing need for sparse deep learning, model compression techniques, especially pruning, have gained significant attention. However, conventional pruning technique
Externí odkaz:
http://arxiv.org/abs/2312.10181
Autor:
Yin, Lu, Li, Gen, Fang, Meng, Shen, Li, Huang, Tianjin, Wang, Zhangyang, Menkovski, Vlado, Ma, Xiaolong, Pechenizkiy, Mykola, Liu, Shiwei
Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for the entire training process as well as inference. Dynamic sparse training (DST), as a leading sparse training approach, can train deep
Externí odkaz:
http://arxiv.org/abs/2305.19454
Lottery Ticket Hypothesis (LTH) claims the existence of a winning ticket (i.e., a properly pruned sub-network together with original weight initialization) that can achieve competitive performance to the original dense network. A recent work, called
Externí odkaz:
http://arxiv.org/abs/2305.02190