Machine learning and computational mathematics
From MaRDI portal
Abstract: Neural network-based machine learning is capable of approximating functions in very high dimension with unprecedented efficiency and accuracy. This has opened up many exciting new possibilities, not just in traditional areas of artificial intelligence, but also in scientific computing and computational science. At the same time, machine learning has also acquired the reputation of being a set of "black box" type of tricks, without fundamental principles. This has been a real obstacle for making further progress in machine learning. In this article, we try to address the following two very important questions: (1) How machine learning has already impacted and will further impact computational mathematics, scientific computing and computational science? (2) How computational mathematics, particularly numerical analysis, {can} impact machine learning? We describe some of the most important progress that has been made on these issues. Our hope is to put things into a perspective that will help to integrate machine learning with computational mathematics.
Recommendations
Cites work
- A mean field view of the landscape of two-layer neural networks
- A priori estimates of the population risk for two-layer neural networks
- Breaking the curse of dimensionality with convex neural networks
- Deep learning-based numerical methods for high-dimensional parabolic partial differential equations and backward stochastic differential equations
- Deep Potential: A General Representation of a Many-Body Potential Energy Surface
- scientific article; zbMATH DE number 3870001 (Why is no real title available?)
- scientific article; zbMATH DE number 140601 (Why is no real title available?)
- Machine learning from a continuous viewpoint. I
- Maximum principle based algorithms for deep learning
- Mean field analysis of neural networks: a central limit theorem
- Principles of multiscale modeling
- Solving high-dimensional partial differential equations using deep learning
- The heterogeneous multiscale method
- The heterogeneous multiscale methods
- Uniformly accurate machine learning-based hydrodynamic models for kinetic equations
- Universal approximation bounds for superpositions of a sigmoidal function
Cited in
(44)- Integral equations and machine learning
- Machine-learning the Sato-Tate conjecture
- Monte Carlo fPINNs: deep learning method for forward and inverse problems involving high dimensional fractional partial differential equations
- Neural networks and numerical analysis
- Neural control of discrete weak formulations: Galerkin, least squares \& minimal-residual methods with quasi-optimal weights
- scientific article; zbMATH DE number 1552034 (Why is no real title available?)
- A multi-level procedure for enhancing accuracy of machine learning algorithms
- Generalization Error Analysis of Neural Networks with Gradient Based Regularization
- High Order Deep Neural Network for Solving High Frequency Partial Differential Equations
- VPVnet: a velocity-pressure-vorticity neural network method for the Stokes' equations under reduced regularity
- An Augmented Lagrangian Deep Learning Method for Variational Problems with Essential Boundary Conditions
- A Deep Learning Method for Elliptic Hemivariational Inequalities
- MOD-Net: a machine learning approach via model-operator-data network for solving PDEs
- Mathematics for Machine Learning
- A Local Deep Learning Method for Solving High Order Partial Differential Equations
- Machine Learning and Invariant Theory
- Machine Learning in Pure Mathematics and Theoretical Physics
- A Chebyshev Polynomial Neural Network Solver for Boundary Value Problems of Elliptic Equations
- A Hybrid Method for Three-Dimensional Semi-Linear Elliptic Equations
- A mathematical perspective of machine learning
- DPK: Deep Neural Network Approximation of the First Piola-Kirchhoff Stress
- Convergence Analysis of a Quasi-Monte CarloBased Deep Learning Algorithm for Solving Partial Differential Equations
- Improved Analysis of PINNs: Alleviate the CoD for Compositional Solutions
- DNN-HDG: a deep learning hybridized discontinuous Galerkin method for solving some elliptic problems
- Subspace decomposition based DNN algorithm for elliptic type multi-scale PDEs
- Port-metriplectic neural networks: thermodynamics-informed machine learning of complex physical systems
- Failure-Informed Adaptive Sampling for PINNs
- A MCMC method based on surrogate model and Gaussian process parameterization for infinite Bayesian PDE inversion
- Failure-informed adaptive sampling for PINNs. II: Combining with re-sampling and subset simulation
- Computing ground states of Bose-Einstein condensation by normalized deep neural network
- Adaptive neural network basis methods for partial differential equations with low-regular solutions
- R-adaptive DeepONet: learning solution operators for PDEs with discontinuous solutions using an R-adaptive strategy
- DRM revisited: a complete error analysis
- A radial basis function neural network approach for solving a diffusion partial differential equation efficiently
- Implicit bias in understanding deep learning for solving PDEs beyond Ritz-Galerkin method
- A hybrid iterative method for elliptic variational inequalities of the second kind
- On understanding and overcoming spectral biases of deep neural network learning methods for solving PDEs
- An adaptive energy-based sequential method for training PINNs to solve gradient flow equations
- An unsupervised K-means machine learning algorithm via overlapping to improve the nodes selection for solving elliptic problems
- Tensor neural network and its numerical integration
- Convergence rates for random feature neural network approximation in molecular dynamics
- Physics-informed multiresolution wavelet neural network method for solving partial differential equations
- SOR-unrolled learning-to-solve method for absolute value equations
- MCMC-PINNs: adaptively sampling collocation points of PINNs with an improved Markov chain Monte Carlo method
This page was built for publication: Machine learning and computational mathematics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5162355)
