Fredholm Neural Networks for inverse problems in elliptic PDEs
Not on the map. Why?
Abstract (arXiv)
Building on our previous work on Fredholm Neural Networks (Fredholm NNs/ FNNs) for solving integral equations, we extend the framework to inverse problems for linear and nonlinear elliptic partial differential equations. The proposed scheme consists of a custom-designed deep neural network (DNN) in which the number of layers, weights, biases and hyperparameters are computed in an explainable manner based on a fixed-point scheme, and we therefore refer to this as the Potential Fredholm Neural Network (PFNN). We first build the PFNN as a method for solving the forward problem, showing that this approach ensures both a high accuracy and explainability, achieving small errors in the interior of the domain, and near machine-precision on the boundary. We then use this approach to solve inverse problems for elliptic PDEs, and provide a rigorous proof for the consistency of the scheme and error bounds for both the interior and boundary of the domain, tied directly to the architecture of the PFNN. In particular, we show that these error bounds depend on the approximation of the boundary function and the integral discretization scheme, both of which directly correspond to components of the Fredholm NN architecture. In this way, we construct an explainable scheme that provides accurate solutions to the inverse problems, whilst still explicitly respecting the boundary conditions, due to the architecture of the PFNN. We assess the performance of the proposed scheme for linear and semi-linear elliptic PDEs in two and three dimensions.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 34 of its 78 references that are in the map. First posted on arXiv 8 Jul 2025.
Builds on
34 of 78 references.
References · 34
- 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,908
- 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 2,018
- 2024KAN: Kolmogorov-Arnold Networkscited by 649
- 2021Characterizing possible failure modes in physics-informed neural networkscited by 643
- 2020When and why PINNs fail to train: A neural tangent kernel perspectivecited by 634
- 2019DeepXDE: A deep learning library for solving differential equationscited by 619
- 2017Solving high-dimensional partial differential equations using deep learningcited by 556
- 2020Multipole Graph Neural Operator for Parametric Partial Differential Equationscited by 349
- 2021Solving and Learning Nonlinear PDEs with Gaussian Processescited by 129
- 2020Hyper-Parameter Optimization: A Review of Algorithms and Applicationscited by 114
- 2020Local Extreme Learning Machines and Domain Decomposition for Solving Linear and Nonlinear Partial Differential Equationscited by 81
- 2021Stiff Neural Ordinary Differential Equationscited by 78
22 more
- 2022Generic bounds on the approximation error for physics-informed (and) operator learningcited by 65
- 2024KAN-ODEs: Kolmogorov-Arnold Network Ordinary Differential Equations for Learning Dynamical Systems and Hidden Physicscited by 59
- 2021Error analysis for physics informed neural networks (PINNs) approximating Kolmogorov PDEscited by 57
- 2022Blending Neural Operators and Relaxation Methods in PDE Numerical Solverscited by 54
- 2019Coarse-scale PDEs from fine-scale observations via machine learningcited by 35
- 2022Constructing coarse-scale bifurcation diagrams from spatio-temporal observations of microscopic simulations: A parsimonious machine learning approachcited by 25
- 2018Neural-net-induced Gaussian process regression for function approximation and PDE solutioncited by 22
- 2023Sampling weights of deep neural networkscited by 20
- 2022Parsimonious Physics-Informed Random Projection Neural Networks for Initial-Value Problems of ODEs and index-1 DAEscited by 19
- 2022Learning black- and gray-box chemotactic PDEs/closures from agent based Monte Carlo simulation datacited by 18
- 2024RandONet: Shallow-Networks with Random Projections for learning linear and nonlinear operatorscited by 16
- 2022Certified machine learning: A posteriori error estimation for physics-informed neural networkscited by 15
- 2021A Modified Batch Intrinsic Plasticity Method for Pre-training the Random Coefficients of Extreme Learning Machinescited by 14
- 2024KKANs: Kurkova-Kolmogorov-Arnold Networks and Their Learning Dynamicscited by 13
- 2024SPIKANs: Separable Physics-Informed Kolmogorov-Arnold Networkscited by 12
- 2021Personalized Algorithm Generation: A Case Study in Learning ODE Integratorscited by 9
- 2022Certified machine learning: Rigorous a posteriori error bounds for PDE defined PINNscited by 8
- 2022A Recursively Recurrent Neural Network (R2N2) Architecture for Learning Iterative Algorithmscited by 8
- 2024Solving Partial Differential Equations in Different Domains by Operator Learning method Based on Boundary Integral Equationscited by 4
- 2024Error estimation for physics-informed neural networks with implicit Runge-Kutta methodscited by 2
- 2024Exact and approximate error bounds for physics-informed neural networkscited by 2
- 2022Neural Network Representation of Time Integratorscited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.