Solution of nonlinear ordinary differential equations by feedforward neural networks

DOI10.1016/0895-7177(94)00160-XzbMath0818.65077OpenAlexW1970346034WikidataQ56970928 ScholiaQ56970928MaRDI QIDQ1344634

A. A. Fernandez, Andrew J. jun. Meade

Publication date: 13 February 1995

Published in: Mathematical and Computer Modelling (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/0895-7177(94)00160-x

zbMATH Keywords

numerical examplesboundary value problemneural computationnonlinear ordinary differential equationsfeedforward neural networks

Mathematics Subject Classification ID

Nonlinear boundary value problems for ordinary differential equations (34B15) Neural networks for/in biological studies, artificial life and related topics (92B20) Numerical solution of boundary value problems involving ordinary differential equations (65L10)

Related Items

Int-Deep: a deep learning initialized iterative method for nonlinear problems, Chebyshev neural network based model for solving Lane-Emden type equations, CAN-PINN: a fast physics-informed neural network based on coupled-automatic-numerical differentiation method, Numerical solution for high order differential equations using a hybrid neural network-optimization method, A neural computational intelligence method based on Legendre polynomials for fuzzy fractional order differential equation, On computing the hyperparameter of extreme learning machines: algorithm and application to computational PDEs, and comparison with classical and high-order finite elements, Solving non-linear Kolmogorov equations in large dimensions by using deep learning: a numerical comparison of discretization schemes, BINN: a deep learning approach for computational mechanics problems based on boundary integral equations, Isogeometric neural networks: a new deep learning approach for solving parameterized partial differential equations, Pseudospectral method for second-order autonomous nonlinear differential equations, Physics-informed ConvNet: learning physical field from a shallow neural network, A novel improved extreme learning machine algorithm in solving ordinary differential equations by Legendre neural network methods, Hermite Functional Link Neural Network for Solving the Van der Pol–Duffing Oscillator Equation, Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks, Orthonormal Bernoulli wavelets neural network method and its application in astrophysics, Legendre Neural Network for Solving Linear Variable Coefficients Delay Differential-Algebraic Equations with Weak Discontinuities, Neuro-optimized numerical treatment of HIV infection model, Establishing criteria to ensure successful feedforward artificial neural network modelling of mechanical systems, Integration modified wavelet neural networks for solving thin plate bending problem, Numerical simulation of Volterra-Fredholm integral equations using least squares support vector regression, Weak adversarial networks for high-dimensional partial differential equations, Approximation properties of local bases assembled from neural network transfer functions

Cites Work

• The numerical solution of linear ordinary differential equations by feedforward neural networks
• Neural algorithm for solving differential equations
• Regularization Algorithms for Learning That Are Equivalent to Multilayer Networks
• Product Approximation for Non-linear Problems in the Finite Element Method
• Approximation by superpositions of a sigmoidal function
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item