Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients

DOI10.1016/j.cma.2021.114188OpenAlexW3202131078WikidataQ114196875 ScholiaQ114196875MaRDI QIDQ2246423

Gianluca Fabiani, Constantinos I. Siettos, Francesco Calabrò

Publication date: 16 November 2021

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2012.05871

zbMATH Keywords

collocation methodsboundary layerartificial neural networkspartial differential equationsextreme learning machinesigmoidal transfer functions

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Spectral, collocation and related methods for initial value and initial-boundary value problems involving PDEs (65M70)

Related Items (15)

Numerical bifurcation analysis of PDEs from lattice Boltzmann model simulations: a parsimonious machine learning approach ⋮ Numerical approximation of partial differential equations by a variable projection method with artificial neural networks ⋮ On computing the hyperparameter of extreme learning machines: algorithm and application to computational PDEs, and comparison with classical and high-order finite elements ⋮ Physics-informed neural networks for 2nd order ODEs with sharp gradients ⋮ Physics-informed neural networks for approximating dynamic (hyperbolic) PDEs of second order in time: error analysis and algorithms ⋮ The Random Feature Method for Time-Dependent Problems ⋮ Time discretization in the solution of parabolic PDEs with ANNs ⋮ A method for computing inverse parametric PDE problems with random-weight neural networks ⋮ An extreme learning machine-based method for computational PDEs in higher dimensions ⋮ A novel physics-informed deep learning strategy with local time-updating discrete scheme for multi-dimensional forward and inverse consolidation problems ⋮ Numerical computation of partial differential equations by hidden-layer concatenated extreme learning machine ⋮ Data-driven control of agent-based models: an equation/variable-free machine learning approach ⋮ Learned Gaussian quadrature for enriched solid finite elements ⋮ A new numerical approach method to solve the Lotka-Volterra predator-prey models with discrete delays ⋮ Solving partial differential equation based on extreme learning machine

Uses Software

• DeepXDE
• DGM

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation by neural networks with scattered data
• Isogeometric collocation for elastostatics and explicit dynamics
• Approximation results for neural network operators activated by sigmoidal functions
• Trends in extreme learning machines: a review
• A collection of 2D elliptic problems for testing adaptive grid refinement algorithms
• A posteriori estimators for the \(h\)-\(p\) version of the finite element method in 1D
• A fully automatic \(hp\)-adaptivity
• Multilayer feedforward networks are universal approximators
• An approximation by neural networks with a fixed weight
• Nonlinearity creates linear independence
• DGM: a deep learning algorithm for solving partial differential equations
• DPM: a deep learning PDE augmentation method with application to large-eddy simulation
• A derivative-free method for solving elliptic partial differential equations with deep neural networks
• On the approximation by single hidden layer feedforward neural networks with fixed weights
• Conservative physics-informed neural networks on discrete domains for conservation laws: applications to forward and inverse problems
• Neural-net-induced Gaussian process regression for function approximation and PDE solution
• Negative results for approximation using single layer and multilayer feedforward neural networks
• Null rules for the detection of lower regularity of functions
• Machine learning for semi linear PDEs
• An accurate FIC-FEM formulation for the 1D advection-diffusion-reaction equation
• Solving high-dimensional partial differential equations using deep learning
• DeepXDE: A Deep Learning Library for Solving Differential Equations
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients