2021
DOI: 10.1007/s11071-021-06819-z
|View full text |Cite
|
Sign up to set email alerts
|

Solving Huxley equation using an improved PINN method

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
5
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
6
1

Relationship

0
7

Authors

Journals

citations
Cited by 15 publications
(6 citation statements)
references
References 34 publications
0
5
0
1
Order By: Relevance
“…From Figure 4, we can see that with the increase in regional configuration points 1000, 2000,3000, 4000 f N = , the fitting effect of the exact rogue wave solution and predicted rogue wave solution is getting better and better. In order to study the influence of sampling point f N on the relative norm error of ( ) ( ) ( ) , , , , , u t x v t x q t x of the improved physical information neural network, when the fixed network has 8 hidden layers and their neurons (10,15,20,25,30), the corresponding norm error is shown in Figures 5(a)-(e). From the figure, we can see that the relative norm error ( ( ) ( ) ( ) , , , , , u t x v t x q t x ) roughly shows a decreasing trend with the increase of f N .…”
Section: Loss Loss Loss Loss Lossmentioning
confidence: 99%
See 1 more Smart Citation
“…From Figure 4, we can see that with the increase in regional configuration points 1000, 2000,3000, 4000 f N = , the fitting effect of the exact rogue wave solution and predicted rogue wave solution is getting better and better. In order to study the influence of sampling point f N on the relative norm error of ( ) ( ) ( ) , , , , , u t x v t x q t x of the improved physical information neural network, when the fixed network has 8 hidden layers and their neurons (10,15,20,25,30), the corresponding norm error is shown in Figures 5(a)-(e). From the figure, we can see that the relative norm error ( ( ) ( ) ( ) , , , , , u t x v t x q t x ) roughly shows a decreasing trend with the increase of f N .…”
Section: Loss Loss Loss Loss Lossmentioning
confidence: 99%
“…Subsequently, based on the work of Jagtap A. D., the team of Chen Yong used the PINN algorithm with an adaptive activation function to study the problem of solving differential equations and named it IPINN [23]. We also studied the rogue wave solution [24] and the soliton solution [25] using by IPINN method. Although the PINN algorithm and its improvement have made some achievements, the research of these new algorithms on differential systems is much more than that.…”
Section: Introductionmentioning
confidence: 99%
“…However, the process of solving PDEs is extremely difficult, traditional numerical methods are very complex and require a lot of computation. Researchers have proved that it can obtain approximate solutions faster than traditional PDE solvers through neural network experiments [3], such as Convolutional Neural Networks [4], Recurrent Neural Network [5], Generative Adversarial Networks [6], DeepONet [7], physic informed neural network (PINN) [8][9][10] and so on. Recently, Zhang [11] et al proposed the Bilinear Neural Network Method (BNNM) for investigating the analytical solutions of PDEs based on the bilinear method and the Neural Network model.…”
Section: Introductionmentioning
confidence: 99%
“…This discusses the approximation ability of neural network. Under this circumstance, there have been early works [33,34], the works of [35,36] and the popular PINN methods of [37][38][39][40][41][42][43], etc. While PINN methods are successful for elliptic type PDEs, the method is inefficient for time evolution problems due to its approximation is limited to a fixed time window.…”
Section: Introductionmentioning
confidence: 99%