Multilayer feedforward networks are universal approximators
From MaRDI portal
Publication:1708845
DOI10.1016/0893-6080(89)90020-8zbMath1383.92015DBLPjournals/nn/HornikSW89OpenAlexW2137983211WikidataQ56020518 ScholiaQ56020518MaRDI QIDQ1708845
Kurt Hornik, Halbert White, Maxwell B. Stinchcombe
Publication date: 27 March 2018
Published in: Neural Networks (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0893-6080(89)90020-8
universal approximationStone-Weierstrass theoremfeedforward networksmapping networksback-propagation networksnetwork representation capabilitysigma-pi networkssquashing functions
Neural networks for/in biological studies, artificial life and related topics (92B20) Interpolation in approximation theory (41A05)
Related Items (only showing first 100 items - show all)
A tutorial on optimal control and reinforcement learning methods for quantum technologies ⋮ Chaotic signals inside some tick-by-tick financial time series ⋮ A method for representing periodic functions and enforcing exactly periodic boundary conditions with deep neural networks ⋮ An efficient neural network method with plane wave activation functions for solving Helmholtz equation ⋮ Adaptive two-layer ReLU neural network. I: Best least-squares approximation ⋮ Adaptive two-layer ReLU neural network. II: Ritz approximation to elliptic PDEs ⋮ Interpolation and approximation via momentum ResNets and neural ODEs ⋮ Trend to equilibrium for the kinetic Fokker-Planck equation via the neural network approach ⋮ A derivative-free method for solving elliptic partial differential equations with deep neural networks ⋮ Structure-preserving neural networks ⋮ PhyGeoNet: physics-informed geometry-adaptive convolutional neural networks for solving parameterized steady-state PDEs on irregular domain ⋮ Solving the linear transport equation by a deep neural network approach ⋮ Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows ⋮ SelectNet: self-paced learning for high-dimensional partial differential equations ⋮ DeepM\&Mnet: inferring the electroconvection multiphysics fields based on operator approximation by neural networks ⋮ A statistical model of neural network learning via the Cramer-Rao lower bound ⋮ Metric entropy limits on recurrent neural network learning of linear dynamical systems ⋮ Machine learning for fluid flow reconstruction from limited measurements ⋮ The mixed deep energy method for resolving concentration features in finite strain hyperelasticity ⋮ DeLISA: deep learning based iteration scheme approximation for solving PDEs ⋮ Learning time-dependent PDEs with a linear and nonlinear separate convolutional neural network ⋮ On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling ⋮ RotEqNet: rotation-equivariant network for fluid systems with symmetric high-order tensors ⋮ Mechanistically informed data-driven modeling of cyclic plasticity via artificial neural networks ⋮ A comprehensive and fair comparison of two neural operators (with practical extensions) based on FAIR data ⋮ Physics informed neural networks for continuum micromechanics ⋮ Deep UQ: learning deep neural network surrogate models for high dimensional uncertainty quantification ⋮ Selection dynamics for deep neural networks ⋮ Metamodeling of aircraft infrared signature dispersion ⋮ Using machine learning to improve cylindrical algebraic decomposition ⋮ A non-cooperative meta-modeling game for automated third-party calibrating, validating and falsifying constitutive laws with parallelized adversarial attacks ⋮ A robust solution of a statistical inverse problem in multiscale computational mechanics using an artificial neural network ⋮ SciANN: a Keras/Tensorflow wrapper for scientific computations and physics-informed deep learning using artificial neural networks ⋮ A general deep learning framework for history-dependent response prediction based on UA-Seq2Seq model ⋮ Deep learned finite elements ⋮ Universal machine learning for topology optimization ⋮ A review on computational intelligence for identification of nonlinear dynamical systems ⋮ An enhanced multi-objective evolutionary optimization algorithm with inverse model ⋮ Efficient approximation of solutions of parametric linear transport equations by ReLU DNNs ⋮ Topological properties of the set of functions generated by neural networks of fixed size ⋮ Discretization and machine learning approximation of BSDEs with a constraint on the gains-process ⋮ Hierarchical deep-learning neural networks: finite elements and beyond ⋮ Deep autoencoder based energy method for the bending, vibration, and buckling analysis of Kirchhoff plates with transfer learning ⋮ Approximation by exponential sampling type neural network operators ⋮ Computing Lyapunov functions using deep neural networks ⋮ The universal approximation property. Characterization, construction, representation, and existence ⋮ Solving the chaos model-data paradox in the cryptocurrency market ⋮ Interpolation of sparse high-dimensional data ⋮ Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem ⋮ Fast generalization error bound of deep learning without scale invariance of activation functions ⋮ SSN: learning sparse switchable normalization via SparsestMax ⋮ Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness ⋮ \(k\)-hop graph neural networks ⋮ A pruning feedforward small-world neural network based on Katz centrality for nonlinear system modeling ⋮ Two-hidden-layer feed-forward networks are universal approximators: a constructive approach ⋮ Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems ⋮ An analytic layer-wise deep learning framework with applications to robotics ⋮ On the stability properties of gated recurrent units neural networks ⋮ Pricing equity-linked life insurance contracts with multiple risk factors by neural networks ⋮ Explainable neural network for pricing and universal static hedging of contingent claims ⋮ High-dimensional distribution generation through deep neural networks ⋮ Optimal approximation rate of ReLU networks in terms of width and depth ⋮ An individual claims reserving model for reported claims ⋮ Optimally weighted loss functions for solving PDEs with neural networks ⋮ Reinforcement learning and stochastic optimisation ⋮ Exact imposition of boundary conditions with distance functions in physics-informed deep neural networks ⋮ PhyCRNet: physics-informed convolutional-recurrent network for solving spatiotemporal PDEs ⋮ HiDeNN-TD: reduced-order hierarchical deep learning neural networks ⋮ Fitting small piece-wise linear neural network models to interpolate data sets ⋮ Normalization effects on shallow neural networks and related asymptotic expansions ⋮ A representative volume element network (RVE-net) for accelerating RVE analysis, microscale material identification, and defect characterization ⋮ Rates of approximation by neural network interpolation operators ⋮ Deep reinforcement learning for inventory control: a roadmap ⋮ Three-dimensional microstructure generation using generative adversarial neural networks in the context of continuum micromechanics ⋮ Data-driven solutions and parameter discovery of the Sasa-Satsuma equation via the physics-informed neural networks method ⋮ Neural network models for inflation forecasting: a revisit ⋮ Forecasts of GDP growth and inflation under the influence of the Covid-19 pandemic: the case of Vietnam ⋮ The construction and approximation of ReLU neural network operators ⋮ On the approximation of rough functions with deep neural networks ⋮ Solving ordinary differential equations using an optimization technique based on training improved artificial neural networks ⋮ Adaptive neural control for uncertain constrained pure feedback systems with severe sensor faults: a complexity reduced approach ⋮ Optimal control of PDEs using physics-informed neural networks ⋮ Quantum activation functions for quantum neural networks ⋮ Non-homogeneous Poisson process intensity modeling and estimation using measure transport ⋮ Error bounds for ReLU networks with depth and width parameters ⋮ On stability and regularization for data-driven solution of parabolic inverse source problems ⋮ Neural eikonal solver: improving accuracy of physics-informed neural networks for solving eikonal equation in case of caustics ⋮ Nonlinear input feature reduction for data-based physical modeling ⋮ The nonlinear wave solutions and parameters discovery of the Lakshmanan-Porsezian-Daniel based on deep learning ⋮ Deep learning Gauss-Manin connections ⋮ Spatiotemporally dynamic implicit large eddy simulation using machine learning classifiers ⋮ Data-driven predictions of the Lorenz system ⋮ A new mesh smoothing method based on a neural network ⋮ A theoretical analysis of deep neural networks and parametric PDEs ⋮ Nonlinear approximation and (deep) ReLU networks ⋮ Neural network identifiability for a family of sigmoidal nonlinearities ⋮ Approximation spaces of deep neural networks ⋮ Universal approximations of invariant maps by neural networks ⋮ Exponential ReLU DNN expression of holomorphic maps in high dimension ⋮ Best \(k\)-layer neural network approximations
Cites Work
This page was built for publication: Multilayer feedforward networks are universal approximators
