Neural-net-induced Gaussian process regression for function approximation and PDE solution

DOI10.1016/j.jcp.2019.01.045zbMath1451.68242arXiv1806.11187OpenAlexW2811199191WikidataQ128346412 ScholiaQ128346412MaRDI QIDQ2214653

Yanyan Li

Publication date: 10 December 2020

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1806.11187

zbMATH Keywords

neural networkpartial differential equationmachine learninguncertainty quantificationGaussian process induced by neural network

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Neural nets and related approaches to inference from stochastic processes (62M45) PDEs in connection with computer science (35Q68)

Related Items (17)

B-PINNs: Bayesian physics-informed neural networks for forward and inverse PDE problems with noisy data ⋮ Symplectic neural networks in Taylor series form for Hamiltonian systems ⋮ Multi-fidelity Bayesian neural networks: algorithms and applications ⋮ Physics-informed neural networks for high-speed flows ⋮ Three ways to solve partial differential equations with neural networks — A review ⋮ Discontinuity computing using physics-informed neural networks ⋮ Learning elliptic partial differential equations with randomized linear algebra ⋮ Deep learning of vortex-induced vibrations ⋮ Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients ⋮ Physics-Informed Generative Adversarial Networks for Stochastic Differential Equations ⋮ Parametric Gaussian process regression for big data ⋮ Integrated Lagrangian and Eulerian 3D microstructure-explicit simulations for predicting macroscopic probabilistic SDT thresholds of energetic materials ⋮ Interpretable machine learning: fundamental principles and 10 grand challenges ⋮ Constraint-aware neural networks for Riemann problems ⋮ Variational inference for nonlinear inverse problems via neural net kernels: comparison to Bayesian neural networks, application to topology optimization ⋮ Monte Carlo fPINNs: deep learning method for forward and inverse problems involving high dimensional fractional partial differential equations ⋮ Learning and meta-learning of stochastic advection–diffusion–reaction systems from sparse measurements

Uses Software

• GPML
• George

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Spectral and finite difference solutions of the Burgers equations
• Inferring solutions of differential equations using noisy multi-fidelity data
• Machine learning of linear differential equations using Gaussian processes
• Discovering variable fractional orders of advection-dispersion equations from field data using multi-fidelity Bayesian optimization
• Bayesian learning for neural networks
• Computational investigations of low-discrepancy sequences

This page was built for publication: Neural-net-induced Gaussian process regression for function approximation and PDE solution