Deep learning: an introduction for applied mathematicians
From MaRDI portal
(Redirected from Publication:5243183)
Abstract: Multilayered artificial neural networks are becoming a pervasive tool in a host of application fields. At the heart of this deep learning revolution are familiar concepts from applied and computational mathematics; notably, in calculus, approximation theory, optimization and linear algebra. This article provides a very brief introduction to the basic ideas that underlie deep learning from an applied mathematics perspective. Our target audience includes postgraduate and final year undergraduate students in mathematics who are keen to learn about the area. The article may also be useful for instructors in mathematics who wish to enliven their classes with references to the application of deep learning techniques. We focus on three fundamental questions: what is a deep neural network? how is a network trained? what is the stochastic gradient method? We illustrate the ideas with a short MATLAB code that sets up and trains a network. We also show the use of state-of-the art software on a large scale image classification problem. We finish with references to the current literature.
Recommendations
Cites work
- Deep learning
- Evaluating Derivatives
- scientific article; zbMATH DE number 1243473 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Matlab guide
- Optimization methods for large-scale machine learning
- Stochastic gradient descent in continuous time
- Stochastic separation theorems
- Trust Region Algorithms and Timestep Selection
Cited in
(80)- Deep learning: a Bayesian perspective
- A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element discretizations
- Classification with Runge-Kutta networks and feature space augmentation
- LSPIA, (stochastic) gradient descent, and parameter correction
- PFNN: a penalty-free neural network method for solving a class of second-order boundary-value problems on complex geometries
- Machine learning and reduced order computation of a friction stir welding model
- Physics-informed neural networks for the shallow-water equations on the sphere
- \(S\)-frame discrepancy correction models for data-informed Reynolds stress closure
- Machine learning moment closure models for the radiative transfer equation. I: Directly learning a gradient based closure
- A data-driven shock capturing approach for discontinuous Galerkin methods
- A deep learning approach to the inversion of borehole resistivity measurements
- Computational methods for deep learning. Theoretic, practice and applications
- Adaptive non-intrusive reduced order modeling for compressible flows
- Deep learning as optimal control problems: models and numerical methods
- Discovering phase field models from image data with the pseudo-spectral physics informed neural networks
- Control on the manifolds of mappings with a view to the deep learning
- Deep limits of residual neural networks
- Neural control of discrete weak formulations: Galerkin, least squares \& minimal-residual methods with quasi-optimal weights
- Deep CNNs as universal predictors of elasticity tensors in homogenization
- Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons
- DeepBND: a machine learning approach to enhance multiscale solid mechanics
- Neural ODEs as the deep limit of ResNets with constant weights
- Bilevel optimization, deep learning and fractional Laplacian regularization with applications in tomography
- scientific article; zbMATH DE number 7451142 (Why is no real title available?)
- Matching component analysis for transfer learning
- Algorithmic learning and deep neural networks
- On a multilevel Levenberg-Marquardt method for the training of artificial neural networks and its application to the solution of partial differential equations
- Generalization Error Analysis of Neural Networks with Gradient Based Regularization
- The train of artificial intelligence
- Mathematics of deep learning. An introduction
- Deep unfitted Nitsche method for elliptic interface problems
- Sublinear convergence of a tamed stochastic gradient descent method in Hilbert space
- Mathematical Aspects of Deep Learning
- Book Reviews
- Machine learning and computational mathematics
- Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks
- Solving inverse problems using data-driven models
- Mathematical methods in deep learning
- Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
- An introduction to deep generative modeling
- A literature survey of matrix methods for data science
- Using deep neural networks for detecting spurious oscillations in discontinuous Galerkin solutions of convection-dominated convection-diffusion equations
- Time discretization in the solution of parabolic PDEs with ANNs
- Physics-informed deep learning for simultaneous surrogate modeling and PDE-constrained optimization of an airfoil geometry
- Knowledge-informed neuro-integrators for aggregation kinetics
- Computational Methods for Deep Learning
- Deep learning and geometric deep learning: An introduction for mathematicians and physicists
- Machine learning architectures for price formation models
- Supervised time series classification for anomaly detection in subsea engineering
- A new decision making method for selection of optimal data using the von Neumann-Morgenstern theorem
- Long term dynamics of the subgradient method for Lipschitz path differentiable functions
- An accelerated inexact Newton regularization scheme with a learned feature-selection rule for non-linear inverse problems
- Adaptive sampling points based multi-scale residual network for solving partial differential equations
- Can neural networks learn finite elements?
- Deep learning methods for limited data problems in X-ray tomography
- MODNO: multi-operator learning with distributed neural operators
- Forecasting natural gas prices with spatio-temporal copula-based time series models
- Asymptotic-preserving neural networks for hyperbolic systems with diffusive scaling
- Recent developments in machine learning methods for stochastic control and games
- A hybrid Sobolev gradient method for learning NODEs
- On collocation points for physics-informed neural networks applied to convection-dominated convection-diffusion problems
- A non-intrusive neural-network based BFGS algorithm for parameter estimation in non-stationary elasticity
- On loss functionals for physics-informed neural networks for steady-state convection-dominated convection-diffusion problems
- The mathematics of adversarial attacks in AI -- why deep learning is unstable despite the existence of stable neural networks
- Learning the local density of states of a bilayer moiré material
- DUE: a deep learning framework and library for modeling unknown equations
- Data approximation by neural nets for the MRE inverse problem in the frequency and time domains
- Solving differential equations via artificial neural networks: findings and failures in a model problem
- Diffusion models for generative artificial intelligence: an introduction for applied mathematicians
- Neural network solutions to the critical SQG equations via approximating nonlocal periodic operators
- Representation of practical nonsmooth control Lyapunov functions by piecewise affine functions and neural networks
- A comparison study of supervised learning techniques for the approximation of high dimensional functions and feedback control
- Combining physics-based and data-driven models: advancing the frontiers of research with scientific machine learning
- Step-by-step time discrete physics-informed neural networks with application to a sustainability PDE model
- Towards continuous mathematical models for the analysis of classes of deep neural networks
- Full Lyapunov exponents spectrum with deep learning from single-variable time series
- Discovery of governing equations with recursive deep neural networks
- Neural networks for the approximation of Euler's elastica
- Learning two parameters in fractional Tikhonov regularization method via deep neural networks: application to the inverse problem for the Laplace operator with noisy data
- Physics-informed neural networks for aggregation kinetics
Describes a project that uses
Uses Software
This page was built for publication: Deep learning: an introduction for applied mathematicians
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5243183)
