Approximation of functions and their derivatives: A neural network implementation with applications

DOI10.1016/S0307-904X(99)00006-2zbMath0939.65027MaRDI QIDQ1960876

Yanyan Li

Publication date: 17 January 2000

Published in: Applied Mathematical Modelling (Search for Journal in Brave)

zbMATH Keywords

numerical resultsneural networkboundary element methodpartial derivativesviscoelastic fluid flowspolymeric liquidfunction derivatives approximationplanar Couette and Poiseuille flows

Mathematics Subject Classification ID

Boundary element methods applied to problems in solid mechanics (74S15) Statistical mechanics of polymers (82D60) Nonlinear constitutive equations for materials with memory (74D10) Numerical differentiation (65D25)

Related Items (15)

A Proof that Artificial Neural Networks Overcome the Curse of Dimensionality in the Numerical Approximation of Black–Scholes Partial Differential Equations ⋮ Interpolation and rates of convergence for a class of neural networks ⋮ A decision-making machine learning approach in Hermite spectral approximations of partial differential equations ⋮ Error estimates for deep learning methods in fluid dynamics ⋮ Full error analysis for the training of deep neural networks ⋮ Laplace based Bayesian inference for ordinary differential equation models using regularized artificial neural networks ⋮ Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation ⋮ The solutions of vibration control problems using artificial neural networks ⋮ Approximating smooth functions by deep neural networks with sigmoid activation function ⋮ FEA-AI and AI-AI: Two-Way Deepnets for Real-Time Computations for Both Forward and Inverse Mechanics Problems ⋮ Integration modified wavelet neural networks for solving thin plate bending problem ⋮ BEM-neural network approach for polymeric liquids flow analysis. ⋮ Learning ``best kernels from data in Gaussian process regression. With application to aerodynamics ⋮ Optimal Approximation with Sparsely Connected Deep Neural Networks ⋮ Approximation spaces of deep neural networks

Uses Software

• PVM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A finite volume technique to simulate the flow of a viscoelastic fluid
• Squeezing a viscoelastic liquid from a wedge: An exact solution
• A new consitutive equation derived from network theory
• An explicit finite volume method for viscoelastic fluid flows
• Multilayer feedforward networks are universal approximators
• Secondary flows in straight ducts of rectangular cross section
• An Algorithm for Least-Squares Estimation of Nonlinear Parameters
• A Nonlinear Network Viscoelastic Model
• Approximation Capability of Layered Neural Networks with Sigmoid Units on Two Layers
• Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives
• A method for the solution of certain non-linear problems in least squares

This page was built for publication: Approximation of functions and their derivatives: A neural network implementation with applications