Zobrazeno 1 - 10
of 45 009
pro vyhledávání: '"Meta learning"'
Autor:
Jia, Qitao1 (AUTHOR), Xia, Yuanling2 (AUTHOR), Dong, Fanglin1 (AUTHOR), Li, Weihua1 (AUTHOR) liweihua@ynu.edu.cn
Publikováno v:
Briefings in Bioinformatics. Sep2024, Vol. 25 Issue 5, p1-10. 10p.
Autor:
Lv, Xiaomin1 (AUTHOR) lvxiaomin@zjsru.edu.cn, Fang, Kai2 (AUTHOR) kaifang@zafu.edu.cn, Liu, Tongcun2 (AUTHOR) lvxiaomin@zjsru.edu.cn
Publikováno v:
Sensors (14248220). Sep2024, Vol. 24 Issue 17, p5510. 13p.
Autor:
Gharoun, Hassan1 (AUTHOR) hassan.gharoun@student.uts.edu.au, Momenifar, Fereshteh2 (AUTHOR) 22046851@student.westernsydney.edu.au, Chen, Fang1 (AUTHOR) fang.chen@uts.edu.au, Gandomi, Amir3 (AUTHOR) gandomi@uts.edu.au
Publikováno v:
ACM Computing Surveys. Dec2024, Vol. 56 Issue 12, p1-41. 41p.
Autor:
Wei, Baoguo1 (AUTHOR) wbg@nwpu.edu.cn, Wang, Xinyu1 (AUTHOR), Su, Yuetong1 (AUTHOR), Zhang, Yue1 (AUTHOR), Li, Lixin1 (AUTHOR)
Publikováno v:
Sensors (14248220). Sep2024, Vol. 24 Issue 17, p5620. 19p.
Autor:
Block, Jacob L., Srinivasan, Sundararajan, Collins, Liam, Mokhtari, Aryan, Shakkottai, Sanjay
The power of foundation models (FMs) lies in their capacity to learn highly expressive representations that can be adapted to a broad spectrum of tasks. However, these pretrained models require multiple stages of fine-tuning to become effective for d
Externí odkaz:
http://arxiv.org/abs/2410.22264
Autor:
Yang, Yuzhe, Du, Yipeng, Farhan, Ahmad, Angione, Claudio, Zhao, Yue, Yang, Harry, Johnston, Fielding, Buban, James, Colangelo, Patrick
The deployment of large-scale models, such as large language models (LLMs) and sophisticated image generation systems, incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to scalability
Externí odkaz:
http://arxiv.org/abs/2410.21340
Autor:
Wang, Jinze, Zhang, Tiehua, Chai, Boon Xian, Di Pietro, Adriano, Georgakopoulos, Dimitrios, Jin, Jiong
The accurate diagnosis of machine breakdowns is crucial for maintaining operational safety in smart manufacturing. Despite the promise shown by deep learning in automating fault identification, the scarcity of labeled training data, particularly for
Externí odkaz:
http://arxiv.org/abs/2410.20351