Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Yuxian Qiu"'
Autor:
Yao Yang, Yuxian Qiu, Yu Cheng, Ting Yu, Maoyuan Zhu, Wenzhang Qian, Shun Gao, Guoqing Zhuang
Publikováno v:
Horticulturae, Vol 10, Iss 8, p 784 (2024)
Mineral elements and non-structural carbohydrates (NSCs) are important nutrients and energy sources for flower development in plants. However, no studies were reported on the dynamic changes of nutrient stoichiometry and NSC contents in Houpoea offic
Externí odkaz:
https://doaj.org/article/01db779d159f40fd90181a07046334ac
Autor:
Cong Guo, Yuxian Qiu, Jingwen Leng, Chen Zhang, Ying Cao, Quanlu Zhang, Yunxin Liu, Fan Yang, Minyi Guo
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN). Many novel and sophisticated activation functions have been proposed to improve the DNN accuracy but also consume massive memory i
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f50495ab173662137922a8cef854bcf5
http://arxiv.org/abs/2209.10778
http://arxiv.org/abs/2209.10778
Publikováno v:
IEEE Computer Architecture Letters. 18:47-50
Frame latency in continuous vision significantly impacts the agility of intelligent machines that interact with the environment via cameras. However, today's continuous vision systems limit the frame latency due to their fundamental sequential execut
Publikováno v:
ACM Transactions on Architecture and Code Optimization. 15:1-26
Parallel computers now start to adopt Bandwidth-Asymmetric Memory architecture that consists of traditional DRAM memory and new High Bandwidth Memory (HBM) for high memory bandwidth. However, existing task schedulers suffer from low bandwidth usage a
Publikováno v:
MICRO
Deep learning is vulnerable to adversarial attacks, where carefully-crafted input perturbations could mislead a well-trained Deep Neural Network (DNN) to produce incorrect results. Adversarial attacks jeopardize the safety, security, and privacy of D
Publikováno v:
PACT
Continuous vision is the cornerstone of a diverse range of intelligent applications found on emerging computing platforms such as autonomous machines and Augmented Reality glasses. A critical issue in today's continuous vision systems is their long e
Autor:
Bo Yang Hsueh, Yue Guan, Xipeng Li, Zehuan Wang, Yuhao Zhu, Minyi Guo, Yuxian Qiu, Jingwen Leng, Cong Guo, Xiaoying Jia
Publikováno v:
SC
Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weights, leading to irregular computations. Consequently, sparse models ca
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c2be78e3318eb25f94bc22e82fc8075
Publikováno v:
CVPR
Recently, researchers have started decomposing deep neural network models according to their semantics or functions. Recent work has shown the effectiveness of decomposed functional blocks for defending adversarial attacks, which add small input pert
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::85a1b1a9288782716160f85a7a3949e0