Deep learning: an introduction for applied mathematicians
From MaRDI portal
Publication:5243183
DOI10.1137/18M1165748zbMATH Open1440.68214arXiv1801.05894OpenAlexW2963459284WikidataQ126836083 ScholiaQ126836083MaRDI QIDQ5243183FDOQ5243183
Authors: Catherine F. Higham, Desmond J. Higham 
Publication date: 15 November 2019
Published in: SIAM Review (Search for Journal in Brave)
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.
Full work available at URL: https://arxiv.org/abs/1801.05894
Recommendations
supervised learningsigmoidconvolutionneural networkchain rulebackpropagationimage classificationoverfittingstochastic gradient method
Numerical optimization and variational techniques (65K10) Learning and adaptive systems in artificial intelligence (68T05) Artificial neural networks and deep learning (68T07) Algorithms for approximation of functions (65D15)
Cites Work
Cited In (58)
- 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
- Recent developments in machine learning methods for stochastic control and games
- A hybrid Sobolev gradient method for learning NODEs
- Bilevel optimization, deep learning and fractional Laplacian regularization with applications in tomography
- A machine-learning minimal-residual (ML-MRes) framework for goal-oriented finite element discretizations
- Physics-informed deep learning for simultaneous surrogate modeling and PDE-constrained optimization of an airfoil geometry
- 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
- Computational methods for deep learning. Theoretic, practice and applications
- Uncertainty quantification in scientific machine learning: methods, metrics, and comparisons
- Control on the manifolds of mappings with a view to the deep learning
- Mathematical methods in deep learning
- Machine learning and computational mathematics
- The train of artificial intelligence
- Deep unfitted Nitsche method for elliptic interface problems
- Deep limits of residual neural networks
- 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
- A data-driven shock capturing approach for discontinuous Galerkin methods
- Asymptotic-preserving neural networks for hyperbolic systems with diffusive scaling
- Generalization Error Analysis of Neural Networks with Gradient Based Regularization
- Can neural networks learn finite elements?
- 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
- Adaptive non-intrusive reduced order modeling for compressible flows
- Deep learning as optimal control problems: models and numerical methods
- Book Reviews
- 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
- A literature survey of matrix methods for data science
- Title not available (Why is that?)
- 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
- Mathematical Aspects of Deep Learning
- Classification with Runge-Kutta networks and feature space augmentation
- 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
- 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
- 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
- Knowledge-informed neuro-integrators for aggregation kinetics
- 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
- Mathematics of deep learning. An introduction
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)
