The numerical solution of linear ordinary differential equations by feedforward neural networks
From MaRDI portal
artificial neural networkfeedforward neural networkhard limit transfer functionLagrange polynomial splinesmethod of weighted residualssupervised learning
Numerical methods for initial value problems involving ordinary differential equations (65L05) Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Applications of graph theory to circuits and networks (94C15)
The possibility to construct directly and noniteratively a feedforward neural network to approximate arbitrary linear ordinary differential equations is demonstrated. A function approximation theory, which deals with the problem of approximating or interpolating a continuous, multivariate function is considered to explain in general supervised learning and artificial neural network. Transfer functions and Lagrange polynomial splines are considered as basis functions. Input weights and basis weights are introduced. Transformating the transfer function of the neural networks into splines is considered. The method of weighted residuals is described. The method uses the hard limit transfer function. It is linear in storage and processing time, and the \(L_ 2\) norm of the network approximation error decreases quadratically with the increasing number of hidden layer neurons. Two examples are considered. The first one is a first-order linear ordinary differential equation. The second one is a second-order linear differential equation. The result presented uses the hard limit transfer function.
Recommendations
- Solution of nonlinear ordinary differential equations by feedforward neural networks
- Feedforward neural nets as discretization schemes for ODEs and DAEs
- A numerical solution for an initial value problem for ODE using artificial neural network
- A numerical method for solving ordinary differential equations by using neural network
Cites work
- Approximation by superpositions of a sigmoidal function
- scientific article; zbMATH DE number 3846795 (Why is no real title available?)
- scientific article; zbMATH DE number 3909945 (Why is no real title available?)
- scientific article; zbMATH DE number 4027357 (Why is no real title available?)
- scientific article; zbMATH DE number 3179593 (Why is no real title available?)
- scientific article; zbMATH DE number 3724611 (Why is no real title available?)
- scientific article; zbMATH DE number 46151 (Why is no real title available?)
- scientific article; zbMATH DE number 50262 (Why is no real title available?)
- scientific article; zbMATH DE number 54101 (Why is no real title available?)
- Neural algorithm for solving differential equations
- Regularization algorithms for learning that are equivalent to multilayer networks
- Systems of conservation laws
- The method of weighted residuals and variational principles. With application in fluid mechanics, heat and mass transfer
Cited in
(73)- Solution of nonlinear ordinary differential equations by feedforward neural networks
- Feedforward neural nets as discretization schemes for ODEs and DAEs
- The solutions of vibration control problems using artificial neural networks
- A neural computational intelligence method based on Legendre polynomials for fuzzy fractional order differential equation
- A novel improved extreme learning machine algorithm in solving ordinary differential equations by Legendre neural network methods
- Solvable models of layered neural networks based on their differential structure
- Orthonormal Bernoulli wavelets neural network method and its application in astrophysics
- Pseudo-solution of weight equations in neural networks: application for statistical parameters estimation
- On artificial neural networks approach with new cost functions
- A physics-informed deep learning framework for inversion and surrogate modeling in solid mechanics
- Hierarchical deep-learning neural networks: finite elements and beyond
- INN: interfaced neural networks as an accessible meshless approach for solving interface PDE problems
- On some neural network architectures that can represent viscosity solutions of certain high dimensional Hamilton-Jacobi partial differential equations
- PFNN: a penalty-free neural network method for solving a class of second-order boundary-value problems on complex geometries
- Simple computational strategies for more effective physics-informed neural networks modeling of turbulent natural convection
- A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
- An investigation of approximate solutions for second order ordinary differential equations using sigmoid-weighted neural networks
- Polynomial neural forms using feedforward neural networks for solving differential equations
- The deep parametric PDE method and applications to option pricing
- Overcoming the curse of dimensionality in the numerical approximation of parabolic partial differential equations with gradient-dependent nonlinearities
- Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
- A mesh-free method for interface problems using the deep learning approach
- Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks
- Machine learning for finding suboptimal final times and coherent and incoherent controls for an open two-level quantum system
- Physics-informed neural network for modelling the thermochemical curing process of composite-tool systems during manufacture
- Bi-parametric operator preconditioning
- Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
- Multilayer perceptrons and radial basis function neural network methods for the solution of differential equations: a survey
- On computing the hyperparameter of extreme learning machines: algorithm and application to computational PDEs, and comparison with classical and high-order finite elements
- A deep learning energy method for hyperelasticity and viscoelasticity
- DeepParticle: learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method
- Neural network architectures using min-plus algebra for solving certain high-dimensional optimal control problems and Hamilton-Jacobi PDEs
- An efficient numerical method to solve ordinary differential equations using Fibonacci neural networks
- Solving Dirichlet boundary problems for ODEs via swarm intelligence
- Chebyshev neural network based model for solving Lane-Emden type equations
- scientific article; zbMATH DE number 6342252 (Why is no real title available?)
- Numerical solution of Helmholtz equation by the modified Hopfield finite difference techniques
- Regression-based neural network training for the solution of ordinary differential equations
- Buckling analysis of a beam-column using multilayer perceptron neural network technique
- scientific article; zbMATH DE number 1221486 (Why is no real title available?)
- Design feed forward neural network to solve singular boundary value problems
- PFNN-2: a domain decomposed penalty-free neural network method for solving partial differential equations
- A mesh-less, ray-based deep neural network method for the Helmholtz equation with high frequency
- DeepXDE: a deep learning library for solving differential equations
- Numerical simulations for full history recursive multilevel Picard approximations for systems of high-dimensional partial differential equations
- Hermite functional link neural network for solving the Van der Pol-Duffing oscillator equation
- Three ways to solve partial differential equations with neural networks — A review
- Data-driven vortex solitons and parameter discovery of 2D generalized nonlinear Schrödinger equations with a \(\mathcal{PT}\)-symmetric optical lattice
- An extreme learning machine-based method for computational PDEs in higher dimensions
- Random vibration of hysteretic systems under Poisson white noise excitations
- A Novel Deep Neural Network Algorithm for the Helmholtz Scattering Problem In the Unbounded Domain
- A Variational Neural Network Approach for Glacier Modelling with Nonlinear Rheology
- Physics-informed information field theory for modeling physical systems with uncertainty quantification
- Boundary-safe PINNs extension: application to non-linear parabolic PDEs in counterparty credit risk
- A nonlinear-manifold reduced-order model and operator learning for partial differential equations with sharp solution gradients
- Physics-informed graph neural network emulation of soft-tissue mechanics
- Physics-informed polynomial chaos expansions
- An adaptive discrete physics-informed neural network method for solving the Cahn-Hilliard equation
- Neural-integrated meshfree (NIM) method: a differentiable programming-based hybrid solver for computational mechanics
- Physics-informed neural networks and functional interpolation for stiff chemical kinetics
- Solving distributed-order fractional equations by LS-SVR
- Ensemble of physics-informed neural networks for solving plane elasticity problems with examples
- Modeling of complex dynamic systems using differential neural networks with the incorporation of a priori knowledge
- Fredholm neural networks
- Numerical simulation of nonlinear Liénard's equation via Morgan-Voyce even Fibonacci neural network
- Enriching continuous Lagrange finite element approximation spaces using neural networks
- Integration modified wavelet neural networks for solving thin plate bending problem
- A second order ordinary differential equation accompanied by a wide variety of initial conditions
- On the regularity of linear fractional sub-diffusive pseudo-parabolic equations. The application to its discretization by means of artificial neural networks
- Numerical treatment of nonlinear Emden-Fowler equation using stochastic technique
- Weak adversarial networks for high-dimensional partial differential equations
- Overcoming the curse of dimensionality for some Hamilton-Jacobi partial differential equations via neural network architectures
- Numerical solution for high order differential equations using a hybrid neural network-optimization method
This page was built for publication: The numerical solution of linear ordinary differential equations by feedforward neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1334712)
