Feedforward neural nets as discretization schemes for ODEs and DAEs

DOI10.1016/S0377-0427(97)00085-XzbMath0889.65072OpenAlexW2087262774MaRDI QIDQ1372058

R. Gerstberger, Peter Rentrop

Publication date: 18 June 1998

Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0377-0427(97)00085-x

zbMATH Keywords

iterative algorithmsparallel computationneural netsmultibody system dynamicsnonlinear least squares problemlearning strategyindex-3feedforward neural netsparallel shooting-type algorithm

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Implicit ordinary differential equations, differential-algebraic equations (34A09) Nonlinear ordinary differential equations and systems (34A34) Parallel numerical computation (65Y05) Numerical methods for initial value problems involving ordinary differential equations (65L05)

Related Items

Numerical Analysis for Convergence of a Sample-Wise Backpropagation Method for Training Stochastic Neural Networks

Uses Software

• RODAS

Cites Work

• Unnamed Item
• Unnamed Item
• Parallel-iterated Runge-Kutta methods for stiff ordinary differential equations
• Differential-algebraic equations in vehicle system dynamics
• A nonlinear truck model and its treatment as a multibody system
• Convergence aspects of step-parallel iteration of Runge-Kutta methods
• An approach to nonlinear programming
• Ill-Conditioning in Neural Network Training Problems

This page was built for publication: Feedforward neural nets as discretization schemes for ODEs and DAEs