Polynomial neural forms using feedforward neural networks for solving differential equations

DOI10.1007/978-3-030-87986-0_21zbMath1505.65235OpenAlexW3202725229MaRDI QIDQ2148710

Michael Breuß, Toni Schneidereit

Publication date: 24 June 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-87986-0_21

zbMATH Keywords

differential equationsinitial value problemfeedforward neural networkstrial solution

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Numerical methods for initial value problems involving ordinary differential equations (65L05)

Uses Software

• Adam

Cites Work

• Numerical methods for scientists and engineers.
• The numerical solution of linear ordinary differential equations by feedforward neural networks
• Constructing general partial differential equations using polynomial and neural networks
• An introduction to neural network methods for differential equations
• G-stability is equivalent toA-stability
• Neural‐network‐based approximations for solving partial differential equations

This page was built for publication: Polynomial neural forms using feedforward neural networks for solving differential equations