A Novel Neural Network-Based Approach Comparable to High-Precision Finite Difference Methods

Đã lưu trong:
Chi tiết về thư mục
Xuất bản năm:Axioms vol. 14, no. 1 (2025), p. 75
Tác giả chính: Pei, Fanghua
Tác giả khác: Cao, Fujun, Ge, Yongbin
Được phát hành:
MDPI AG
Những chủ đề:
Truy cập trực tuyến:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Các nhãn: Thêm thẻ
Không có thẻ, Là người đầu tiên thẻ bản ghi này!

MARC

LEADER 00000nab a2200000uu 4500
001 3159334398
003 UK-CbPIL
022 |a 2075-1680 
024 7 |a 10.3390/axioms14010075  |2 doi 
035 |a 3159334398 
045 2 |b d20250101  |b d20251231 
084 |a 231430  |2 nlm 
100 1 |a Pei, Fanghua  |u School of Mathematical Statistics, Ningxia University, Yinchuan 750021, China; <email>371102a29nj.cdb@sin.cn</email> 
245 1 |a A Novel Neural Network-Based Approach Comparable to High-Precision Finite Difference Methods 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Deep learning methods using neural networks for solving partial differential equations (PDEs) have emerged as a new paradigm. However, many of these methods approximate solutions by optimizing loss functions, often encountering convergence issues and accuracy limitations. In this paper, we propose a novel deep learning approach that leverages the expressive power of neural networks to generate basis functions. These basis functions are then used to create trial solutions, which are optimized using the least-squares method to solve for coefficients in a system of linear equations. This method integrates the strengths of streaming PINNs and the traditional least-squares method, offering both flexibility and a high accuracy. We conducted numerical experiments to compare our method with the results of high-order finite difference schemes and several commonly used neural network methods (PINNs, lbPINNs, ELMs, and PIELMs). Thanks to the mesh-less feature of the neural network, it is particularly effective for complex geometries. The numerical results demonstrate that our method significantly enhances the accuracy of deep learning in solving PDEs, achieving error levels comparable to high-accuracy finite difference methods. 
653 |a Finite volume method 
653 |a Accuracy 
653 |a Physics 
653 |a Partial differential equations 
653 |a Deep learning 
653 |a Mathematical analysis 
653 |a Neural networks 
653 |a Adaptability 
653 |a Mathematical models 
653 |a Finite difference method 
653 |a Least squares method 
653 |a Basis functions 
653 |a Numerical analysis 
653 |a Linear equations 
653 |a Boundary conditions 
653 |a Optimization algorithms 
653 |a Efficiency 
700 1 |a Cao, Fujun  |u School of Science, Inner Mongolia University of Science and Technology, Baotou 014010, China 
700 1 |a Ge, Yongbin  |u School of Mathematical Statistics, Ningxia University, Yinchuan 750021, China; <email>371102a29nj.cdb@sin.cn</email>; School of Science, Dalian Minzu University, Dalian 116600, China 
773 0 |t Axioms  |g vol. 14, no. 1 (2025), p. 75 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3159334398/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3159334398/fulltextwithgraphics/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3159334398/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch