Zobrazeno 1 - 10
of 769
pro vyhledávání: '"Peng Can"'
Autor:
WANG Jia-qi, KANG Wen-li, WU Zhong-kun, TANG Rong-xue, PENG Can, DAI Zhi-yong, DONG Ling, PAN Li-na
Publikováno v:
Shipin yu jixie, Vol 38, Iss 8, Pp 7-13 (2022)
Objective： The study aimed to explore the effects of composite probiotics on the intestinal regulation. Methods： By constructing mouse model of constipation, intestinal damage and diarrhea, the intestinal ink propulsion, defecation and intestinal
Externí odkaz:
https://doaj.org/article/fda27ea9e76d4ef58edfe64081710327
Autor:
HE Zhen, YUAN Hong-zhao, ZHANG Li-ping, GENG Mei-mei, XU Li-wei, CHEN Wen, PENG Can, WANG Jiu-rong
Publikováno v:
Zhipu Xuebao, Vol 43, Iss 2, Pp 220-227 (2022)
The majority of soil nitrogen is closely associated with soil organic matter, the cleavage of high molecular weight organic N such as protein to smaller soluble compounds (e.g amino acids) is a key step in the terrestrial N cycle. Therefore, as amino
Externí odkaz:
https://doaj.org/article/5e426ce20ad2486cbfb7bcea28ffcca8
Autor:
Saha, Pramit, Wagner, Felix, Mishra, Divyanshu, Peng, Can, Thakur, Anshul, Clifton, David, Kamnitsas, Konstantinos, Noble, J. Alison
Effective training of large Vision-Language Models (VLMs) on resource-constrained client devices in Federated Learning (FL) requires the usage of parameter-efficient fine-tuning (PEFT) strategies. To this end, we demonstrate the impact of two factors
Externí odkaz:
http://arxiv.org/abs/2411.11912
Node classification with Graph Neural Networks (GNN) under a fixed set of labels is well known in contrast to Graph Few-Shot Class Incremental Learning (GFSCIL), which involves learning a GNN classifier as graph nodes and classes growing over time sp
Externí odkaz:
http://arxiv.org/abs/2411.06634
Publikováno v:
Energy Exploration & Exploitation, Vol 37 (2019)
In this article, the grades of different kinds of energy sources are distinguished. Thus, we put forward an equivalent electric calculation method, which is compliant with the calculation of various energy resources that have different grades. Based
Externí odkaz:
https://doaj.org/article/e44311caaa344c47aa8961febecc52c4
Deep learning models suffer from catastrophic forgetting when being fine-tuned with samples of new classes. This issue becomes even more pronounced when faced with the domain shift between training and testing data. In this paper, we study the critic
Externí odkaz:
http://arxiv.org/abs/2309.13563
Deep learning techniques have become widely utilized in histopathology image classification due to their superior performance. However, this success heavily relies on the availability of substantial labeled data, which necessitates extensive and cost
Externí odkaz:
http://arxiv.org/abs/2212.09977
The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments. The challenge of new task learning is often exacerbated by the scarcity of data for the new categor
Externí odkaz:
http://arxiv.org/abs/2208.00147
Publikováno v:
In Computer Vision and Image Understanding December 2024 249
Publikováno v:
In Applied Energy 15 October 2024 372