研究论文开放获取
When and why PINNs fail to train: A neural tangent kernel perspective
Sifan Wang, Xinling Yu, Paris G. Perdikaris
University of Pennsylvania
来源Journal of Computational Physics
年份2021
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
摘要 · 节选
暂未获取摘要。可打开原文或 PDF，后续可基于全文生成更完整的速读。
逐年被引趋势
5002500
20
21
22
23
24
25
50026
关键指标
1,432
被引次数 · OpenAlex
63.43
领域内被引倍数
同类平均 = 1
同类平均 = 1
前 0.1%
引用位次
同领域 · 同年份 · 同类型
同领域 · 同年份 · 同类型
68
参考文献
Google Scholar 与 OpenAlex 的被引统计范围不同，数值存在差异属正常。
AI 辅助阅读
依据：文献信息
论文问答
当前基于文献信息回答
可就本文提问；依据不足时会说明。
学术脉络
学科主题
物理Model Reduction and Neural Networks
Nuclear reactor physics and engineering · Probabilistic and Robust Engineering Design
参考文献 68
Understanding the difficulty of training deep feedforward neural networks
被引 12,478Xavier Glorot, Yoshua Bengio · 2010
Fundamentals of engineering numerical analysis
被引 324Parviz Moin · Canadian Journal of Civil Engineering · 2002
此处列出前 3 条
引用本文 1,432
Scientific Machine Learning Through Physics–Informed Neural Networks: Where we are and What’s Next
被引 2,727Salvatore Cuomo, Vincenzo Schiano Di Cola, Fabio Giampaolo · Journal of Scientific Computing · 2022
A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics
被引 1,316Ehsan Haghighat, Maziar Raissi, Adrian Moure · Computer Methods in Applied Mechanics and Engineering · 2021
A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications
被引 899Laith H. Alzubaidi, Jinshuai Bai, Aiman Al-Sabaawi · Journal Of Big Data · 2023
按被引量排序，此处列出前 3 条