Regression-based neural network training for the solution of ordinary differential equations

DOI10.1504/IJMMNO.2013.055203zbMath1280.65081OpenAlexW2067440175MaRDI QIDQ391689

S. Chakraverty, Susmita Mall

Publication date: 10 January 2014

Published in: International Journal of Mathematical Modelling and Numerical Optimisation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1504/ijmmno.2013.055203

zbMATH Keywords

numerical examplesregressionfeedforward neural networksback propagationunsupervised algorithm

Mathematics Subject Classification ID

Nonlinear boundary value problems for ordinary differential equations (34B15) Nonlinear ordinary differential equations and systems (34A34) Error bounds for numerical methods for ordinary differential equations (65L70)

Related Items (7)

Chebyshev neural network based model for solving Lane-Emden type equations ⋮ An investigation of approximate solutions for second order ordinary differential equations using sigmoid-weighted neural networks ⋮ Neuro-swarms intelligent computing using Gudermannian kernel for solving a class of second order Lane-Emden singular nonlinear model ⋮ Wavelet neural networks functional approximation and application ⋮ A single layer functional link artificial neural network based on Chebyshev polynomials for neural evaluations of nonlinear \(n\)th order fuzzy differential equations ⋮ Hermite Functional Link Neural Network for Solving the Van der Pol–Duffing Oscillator Equation ⋮ Solving ordinary differential equations using an optimization technique based on training improved artificial neural networks

This page was built for publication: Regression-based neural network training for the solution of ordinary differential equations