中文版 | English

在结果中检索

CSpace

浏览/检索结果: 共3条，第1-3条 帮助

限定条件    
已选(0)清除 条数/页：   排序方式：
Approximation capabilities of measure-preserving neural networks 期刊论文
NEURAL NETWORKS, 2022, 卷号: 147, 页码: 72-80
作者:  Zhu, Aiqing;  Jin, Pengzhan;  Tang, Yifa
收藏  |  浏览/下载：111/0  |  提交时间：2022/06/21
Measure-preserving  Neural networks  Dynamical systems  Approximation theory  
SympNets: Intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems 期刊论文
NEURAL NETWORKS, 2020, 卷号: 132, 页码: 166-179
作者:  Jin, Pengzhan;  Zhang, Zhen;  Zhu, Aiqing;  Tang, Yifa;  Karniadakis, George Em
收藏  |  浏览/下载：142/0  |  提交时间：2021/04/26
Deep learning  Physics-informed  Dynamical systems  Hamiltonian systems  Symplectic maps  Symplectic integrators  
Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness 期刊论文
NEURAL NETWORKS, 2020, 卷号: 130, 页码: 85-99
作者:  Jin, Pengzhan;  Lu, Lu;  Tang, Yifa;  Karniadakis, George Em
收藏  |  浏览/下载：117/0  |  提交时间：2021/01/14
Neural networks  Generalization error  Learnability  Data distribution  Cover complexity  Neural network smoothness