Universal approximation bounds for superpositions of a sigmoidal function

DOI10.1109/18.256500zbMATH Open0818.68126OpenAlexW2166116275MaRDI QIDQ4277151FDOQ4277151

Authors: Andrew R. Barron 

Publication date: 7 February 1994

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/04113e8974341f97258800126d05fd8df2751b7e

Recommendations

• Approximation by superpositions of a sigmoidal function
• Approximation and estimation bounds for artificial neural networks
• Estimation of approximating rate for neural network in \(L^p_w\) spaces
• Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives
• Approximation Capability of Layered Neural Networks with Sigmoid Units on Two Layers

zbMATH Keywords

artificial neural networksKolmogorov \(n\)-widths

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (only showing first 100 items - show all)

• Optimal approximation with sparsely connected deep neural networks
• A methodology for the constructive approximation of nonlinear operators defined on noncompact sets
• Non intrusive reduced order modeling of parametrized PDEs by kernel POD and neural networks
• Approximation with random bases: pro et contra
• Insights into randomized algorithms for neural networks: practical issues and common pitfalls
• Universality of deep convolutional neural networks
• A machine learning framework for data driven acceleration of computations of differential equations
• Title not available (Why is that?)
• Approximation of discontinuous signals by sampling Kantorovich series
• Machine learning from a continuous viewpoint. I
• Geometric Rates of Approximation by Neural Networks
• New insights into Witsenhausen's counterexample
• Instability, complexity, and evolution
• Computing the approximation error for neural networks with weights varying on fixed directions
• Lower estimation of approximation rate for neural networks
• Rates of approximation by ReLU shallow neural networks
• Rates of approximation by neural network interpolation operators
• Approximating and simulating the stochastic growth model: Parameterized expectations, neural networks, and the genetic algorithm
• Adaptive-critic based optimal neuro control synthesis for distributed parameter systems
• Nonlinear dynamical system identification with dynamic noise and observational noise
• Neural networks and seasonality: Some technical considerations
• Nonlinear function approximation: computing smooth solutions with an adaptive greedy algorithm
• Voronovskaja type theorems and high-order convergence neural network operators with sigmoidal functions
• Deep neural network structures solving variational inequalities
• Squared and absolute errors in optimal approximation of nonlinear systems.
• Learning a function from noisy samples at a finite sparse set of points
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Neural networks and logistic regression. II.
• Machine learning approximation algorithms for high-dimensional fully nonlinear partial differential equations and second-order backward stochastic differential equations
• Parameter Estimation of Sigmoid Superpositions: Dynamical System Approach
• A comparative analysis of optimization and generalization properties of two-layer neural network and random feature models under gradient descent dynamics
• Towards long-term prediction
• Neural network with unbounded activation functions is universal approximator
• Geometrical aspects of discrimination by multilayer perceptrons
• Input variable selection in neural network models
• Neural Networks for Localized Approximation
• On estimation of surrogate models for multivariate computer experiments
• Estimates on compressed neural networks regression
• Local greedy approximation for nonlinear regression and neural network training.
• Stein's identity, Fisher information, and projection pursuit: A triangulation
• A deletion/substitution/addition algorithm for classification neural networks, with applications to biomedical data
• Approximation of fuzzy-valued functions by regular fuzzy neural networks and the accuracy analysis
• Explaining consumer choice through neural networks: the stacked generalization approach
• A General Form for Global Dynamical Data Models for Three-Dimensional Systems
• Book Review: A mathematical introduction to compressive sensing
• Title not available (Why is that?)
• Parameter redundancy in neural networks: an application of Chebyshev polynomials
• Markov chain network training and conservation law approximations: Linking microscopic and macroscopic models for evolution
• Model selection in neural networks: some difficulties
• Neural network prediction of load from the morphology of trabecular bone
• On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks
• Deep learning observables in computational fluid dynamics
• Variational training of neural network approximations of solution maps for physical models
• The ridge function representation of polynomials and an application to neural networks
• Neural network modeling of vector multivariable functions in ill-posed approximation problems
• Title not available (Why is that?)
• Direct design from data of optimal filters for LPV systems
• Solving high-dimensional optimal stopping problems using deep learning
• Persistence of excitation conditions in passive learning control
• Saturation classes for MAX-product neural network operators activated by sigmoidal functions
• A better approximation for balls
• Deep distributed convolutional neural networks: universality
• A single hidden layer feedforward network with only one neuron in the hidden layer can approximate any univariate function
• Construct Deep Neural Networks based on Direct Sampling Methods for Solving Electrical Impedance Tomography
• Nonlinear approximation in finite-dimensional spaces
• Convergence properties of cascade correlation in function approximation.
• Radial basis function networks: Generalization in over-realizable and unrealizable scenarios
• Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ
• Limitations of the approximation capabilities of neural networks with one hidden layer
• Optimal approximation of piecewise smooth functions using deep ReLU neural networks
• The construction and approximation of ReLU neural network operators
• Complete stability analysis of a heuristic approximate dynamic programming control design
• Designing neural networks for modeling biological data: a statistical perspective
• Optimization based on quasi-Monte Carlo sampling to design state estimators for non-linear systems
• Schwarz iterative methods: infinite space splittings
• Minimizing sequences for a family of functional optimal estimation problems
• A survey on universal approximation and its limits in soft computing techniques.
• The plane wave method for inverse problems associated with Helmholtz-type equations
• Can dictionary-based computational models outperform the best linear ones?
• Learning semidefinite regularizers
• Interpolation by neural network operators activated by ramp functions
• Optimal control of non-linear systems through hybrid cell-mapping/artificial-neural-networks techniques
• Value and Policy Function Approximations in Infinite-Horizon Optimization Problems
• Some comparisons of complexity in dictionary-based and linear computational models
• Error bounds for suboptimal solutions to kernel principal component analysis
• Universal approximation by hierarchical fuzzy systems
• Estimates of the approximation error using Rademacher complexity: Learning vector-valued functions
• Variable selection in neural network regression models with dependent data: a subsampling approach
• A Classification Paradigm for Distributed Vertically Partitioned Data
• Approximation of functions of finite variation by superpositions of a sigmoidal function.
• An approximation by neural networks with a fixed weight
• New study on neural networks: the essential order of approximation
• Analysis of the rate of convergence of least squares neural network regression estimates in case of measurement errors
• Accuracy of suboptimal solutions to kernel principal component analysis
• Approximation properties of a multilayered feedforward artificial neural network
• A dynamic recurrent neural-network-based adaptive observer for a class of nonlinear systems
• How to determine the minimum number of fuzzy rules to achieve given accuracy: a computational geometric approach to SISO case
• Approximation on anisotropic Besov classes with mixed norms by standard information
• On the approximation of functions by tanh neural networks
• The construction and approximation of feedforward neural network with hyperbolic tangent function

This page was built for publication: Universal approximation bounds for superpositions of a sigmoidal function

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4277151)