Deep learning: an introduction for applied mathematicians
From MaRDI portal
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
- scientific article; zbMATH DE number 1243473 (Why is no real title available?)
- scientific article; zbMATH DE number 5060482 (Why is no real title available?)
- Deep learning
- Evaluating Derivatives
- 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
(79)- Neural network solutions to the critical SQG equations via approximating nonlocal periodic operators
- Mathematics of deep learning. An introduction
- A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element discretizations
- Bilevel optimization, deep learning and fractional Laplacian regularization with applications in tomography
- Physics-informed deep learning for simultaneous surrogate modeling and PDE-constrained optimization of an airfoil geometry
- Representation of practical nonsmooth control Lyapunov functions by piecewise affine functions and neural networks
- Computational methods for deep learning. Theoretic, practice and applications
- On a multilevel Levenberg-Marquardt method for the training of artificial neural networks and its application to the solution of partial differential equations
- Discovering phase field models from image data with the pseudo-spectral physics informed neural networks
- Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons
- Control on the manifolds of mappings with a view to the deep learning
- Deep learning and geometric deep learning: An introduction for mathematicians and physicists
- Machine learning and computational mathematics
- Mathematical methods in deep learning
- The train of artificial intelligence
- Neural networks for the approximation of Euler's elastica
- Combining physics-based and data-driven models: advancing the frontiers of research with scientific machine learning
- Deep unfitted Nitsche method for elliptic interface problems
- Deep limits of residual neural networks
- A data-driven shock capturing approach for discontinuous Galerkin methods
- Step-by-step time discrete physics-informed neural networks with application to a sustainability PDE model
- 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
- Asymptotic-preserving neural networks for hyperbolic systems with diffusive scaling
- Towards continuous mathematical models for the analysis of classes of deep neural networks
- Generalization Error Analysis of Neural Networks with Gradient Based Regularization
- Can neural networks learn finite elements?
- Full Lyapunov exponents spectrum with deep learning from single-variable time series
- 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
- Discovery of governing equations with recursive deep neural networks
- Adaptive non-intrusive reduced order modeling for compressible flows
- Deep learning as optimal control problems: models and numerical methods
- Deep learning methods for limited data problems in X-ray tomography
- Book Reviews
- MODNO: multi-operator learning with distributed neural operators
- Forecasting natural gas prices with spatio-temporal copula-based time series models
- An introduction to deep generative modeling
- Uniformly convex neural networks and non-stationary iterated network Tikhonov (iNETT) method
- Machine learning architectures for price formation models
- Recent developments in machine learning methods for stochastic control and games
- A literature survey of matrix methods for data science
- Learning two parameters in fractional Tikhonov regularization method via deep neural networks: application to the inverse problem for the Laplace operator with noisy data
- scientific article; zbMATH DE number 7451142 (Why is no real title available?)
- 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
- Using deep neural networks for detecting spurious oscillations in discontinuous Galerkin solutions of convection-dominated convection-diffusion equations
- Neural ODEs as the deep limit of ResNets with constant weights
- Sublinear convergence of a tamed stochastic gradient descent method in Hilbert space
- Computational Methods for Deep Learning
- Solving Allen-Cahn and Cahn-Hilliard Equations using the Adaptive Physics Informed Neural Networks
- Classification with Runge-Kutta networks and feature space augmentation
- The mathematics of adversarial attacks in AI -- why deep learning is unstable despite the existence of stable neural networks
- Mathematical Aspects of Deep Learning
- Matching component analysis for transfer learning
- 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
- Time discretization in the solution of parabolic PDEs with ANNs
- Supervised time series classification for anomaly detection in subsea engineering
- Learning the local density of states of a bilayer moiré material
- Physics-informed neural networks for aggregation kinetics
- LSPIA, (stochastic) gradient descent, and parameter correction
- DUE: a deep learning framework and library for modeling unknown equations
- PFNN: a penalty-free neural network method for solving a class of second-order boundary-value problems on complex geometries
- Data approximation by neural nets for the MRE inverse problem in the frequency and time domains
- A deep learning approach to the inversion of borehole resistivity measurements
- Deep learning: a Bayesian perspective
- Long term dynamics of the subgradient method for Lipschitz path differentiable functions
- Solving inverse problems using data-driven models
- Machine learning moment closure models for the radiative transfer equation. I: Directly learning a gradient based closure
- A comparison study of supervised learning techniques for the approximation of high dimensional functions and feedback control
- Solving differential equations via artificial neural networks: findings and failures in a model problem
- Knowledge-informed neuro-integrators for aggregation kinetics
- Diffusion models for generative artificial intelligence: an introduction for applied mathematicians
- A new decision making method for selection of optimal data using the von Neumann-Morgenstern theorem
- DeepBND: a machine learning approach to enhance multiscale solid mechanics
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)
