Using neural networks for approximating functions and equations
In this report, we develop the approximation rates of ReLU neural networks for solutions to the elliptic two-scale problems, the stochastic parabolic initial boundary value problems, and the parametric elliptic problems. We obtain bounds on network complexities - in terms of the depth size and the n...
Saved in:
Main Author: | Li, Yongming |
---|---|
Other Authors: | Hoang Viet Ha |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2019
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/136490 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
Similar Items
-
Generalised polynomial chaos approximation for stochastic fractional partial differential equations
by: Teh, Yu Xuan
Published: (2023) -
Bayesian inverse problems for hyperbolic equations
by: Ng, Jeremy
Published: (2020) -
Superconvergence for the gradient of finite element approximations by L2-projections
by: Heimsund, Bjorn-Ove, et al.
Published: (2009) -
Exponential convergence of spectral approximations and time-domain computation of scattering problems.
by: Zhao, Xiaodan.
Published: (2013) -
Fast numerical methods for image processing based on partial differential equations
by: Duan, Yuping
Published: (2012)