Zobrazeno 1 - 10
of 127
pro vyhledávání: '"Su, Junhao"'
Traditional deep learning relies on end-to-end backpropagation for training, but it suffers from drawbacks such as high memory consumption and not aligning with biological neural networks. Recent advancements have introduced locally supervised learni
Externí odkaz:
http://arxiv.org/abs/2407.05638
Autor:
Su, Junhao, Cai, Changpeng, Zhu, Feiyu, He, Chenghao, Xu, Xiaojie, Guan, Dongzhi, Si, Chenyang
Deep neural networks conventionally employ end-to-end backpropagation for their training process, which lacks biological credibility and triggers a locking dilemma during network parameter updates, leading to significant GPU memory use. Supervised lo
Externí odkaz:
http://arxiv.org/abs/2407.05623
Safety issues at construction sites have long plagued the industry, posing risks to worker safety and causing economic damage due to potential hazards. With the advancement of artificial intelligence, particularly in the field of computer vision, the
Externí odkaz:
http://arxiv.org/abs/2407.00906
Autor:
Zhang, Yuming, Zhang, Shouxin, Wang, Peizhe, Zhu, Feiyu, Guan, Dongzhi, Su, Junhao, Liu, Jiabin, Cai, Changpeng
Deep neural networks (DNNs) typically employ an end-to-end (E2E) training paradigm which presents several challenges, including high GPU memory consumption, inefficiency, and difficulties in model parallelization during training. Recent research has
Externí odkaz:
http://arxiv.org/abs/2406.16633
Autor:
Zhu, Feiyu, Zhang, Yuming, Cai, Changpeng, Guo, Guinan, Li, Jiao, Guo, Xiuyuan, Zhang, Quanwei, Wang, Peizhe, He, Chenghao, Su, Junhao
Traditional deep neural networks typically use end-to-end backpropagation, which often places a big burden on GPU memory. Another promising training method is local learning, which involves splitting the network into blocks and training them in paral
Externí odkaz:
http://arxiv.org/abs/2406.00446
Autor:
Cai, Changpeng, Guo, Guinan, Li, Jiao, Su, Junhao, He, Chenghao, Xiao, Jing, Chen, Yuanxu, Dai, Lei, Zhu, Feiyu
Most earlier investigations on talking face generation have focused on the synchronization of lip motion and speech content. However, human head pose and facial emotions are equally important characteristics of natural human faces. While audio-driven
Externí odkaz:
http://arxiv.org/abs/2405.07257
Autor:
Wu, Yuanyuan, Ma, Yuehao, Su, Junhao, Yang, Fengming, Zhang, Wencong, Zhang, Chen, Yang, Yang, Zhu, Huacheng
Publikováno v:
In Case Studies in Thermal Engineering September 2024 61
Autor:
He, Qi, Tan, Bin, Li, Meng, Su, Junhao, Lin, Bing, Wu, Nan-ping, Shen, Hao-nan, Chen, Jia-jing, Zhang, Qian
Publikováno v:
In Environmental Research 15 August 2024 255
Autor:
He, Qi, Zhang, Qian, Su, Junhao, Li, Meng, Lin, Bing, Wu, Nanping, Shen, Haonan, Chen, Jiajing
Publikováno v:
In Chemosphere August 2024 362
Autor:
Xu, Liaoyuan, Su, Junhao, Chen, Haoming, Ye, Jinghua, Qin, Kun, Zhang, Wencong, Yang, Yang, Zhu, Huacheng
Publikováno v:
In Innovative Food Science and Emerging Technologies January 2024 91