Universal approximation bounds for superpositions of a sigmoidal function

DOI10.1109/18.256500zbMATH Open0818.68126OpenAlexW2166116275MaRDI QIDQ4277151FDOQ4277151

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)

• Greedy approximation in convex optimization
• Greedy algorithms for prediction
• Boosting the margin: a new explanation for the effectiveness of voting methods
• Efficient sampling in approximate dynamic programming algorithms
• Information Geometry of U-Boost and Bregman Divergence
• MgNet: a unified framework of multigrid and convolutional neural network
• Exponential screening and optimal rates of sparse estimation
• On the curse of dimensionality in the Ritz method
• Degree of Approximation Results for Feedforward Networks Approximating Unknown Mappings and Their Derivatives
• Approximation order to a function in \(\overline C({\mathbb R})\) by superposition of a sigmoidal function
• A comparison between fixed-basis and variable-basis schemes for function approximation and functional optimization
• Approximation of functions of finite variation by superpositions of a sigmoidal function.
• An approximation by neural networks with a fixed weight
• Computation and learning in high dimensions. Abstracts from the workshop held August 1--7, 2021 (hybrid meeting)
• Mean-field Langevin dynamics and energy landscape of neural networks
• Functional aggregation for nonparametric regression.
• An exponential inequality under weak dependence
• Another look at statistical learning theory and regularization
• Multivariate extensions of isotonic regression and total variation denoising via entire monotonicity and Hardy-Krause variation
• Approximation by network operators with logistic activation functions
• High-dimensional change-point estimation: combining filtering with convex optimization
• Moving-horizon state estimation for nonlinear discrete-time systems: new stability results and approximation schemes
• Low-rank kernel approximation of Lyapunov functions using neural networks
• Approximation by superpositions of a sigmoidal function
• Approximation results for neural network operators activated by sigmoidal functions
• Estimation of the binary response model using a mixture of distributions estimator (MOD)
• Approximating networks and extended Ritz method for the solution of functional optimization problems
• Approximation by max-product neural network operators of Kantorovich type
• Trigonometric RBF neural robust controller design for a class of nonlinear system with linear input unmodeled dynamics
• On Kolmogorov's representation of functions of several variables by functions of one variable
• Title not available (Why is that?)
• Adaptive importance sampling for control and inference
• Linear and nonlinear approximation of spherical radial basis function networks
• Analog quantum computing (AQC) and the need for time-symmetric physics
• Estimates of variation with respect to a set and applications to optimization problems
• Approximation schemes for functional optimization problems
• Multivariate neural network operators with sigmoidal activation functions
• Approximation by perturbed neural network operators
• Boosting with early stopping: convergence and consistency
• Aggregation for Gaussian regression
• The approximation operators with sigmoidal functions
• Approximation and learning by greedy algorithms
• Set membership identification of nonlinear systems
• Multivariate sigmoidal neural network approximation
• Error bounds for approximation with neural networks
• Some remarks on greedy algorithms
• On Approximation by Neural Networks with Optimized Activation Functions and Fixed Weights
• Harmonic analysis of neural networks
• Greedy algorithms and \(M\)-term approximation with regard to redundant dictionaries
• Title not available (Why is that?)
• A receding-horizon regulator for nonlinear systems and a neural approximation
• Uniform approximation by neural networks
• Parametric identification of structured nonlinear systems
• Rescaled pure greedy algorithm for Hilbert and Banach spaces
• On simultaneous approximations by radial basis function neural networks
• The convex geometry of linear inverse problems
• Neural network operators: constructive interpolation of multivariate functions
• Simultaneous greedy approximation in Banach spaces
• Artificial neural networks: an econometric perspective^∗
• Convergence and rate of convergence of some greedy algorithms in convex optimization
• Some problems in the theory of ridge functions
• Approximation with neural networks activated by ramp sigmoids
• On best approximation of classes by radial functions
• Information-theoretic determination of minimax rates of convergence
• Essential rate for approximation by spherical neural networks
• Nonlinear black-box modeling in system identification: A unified overview
• Regularized vector field learning with sparse approximation for mismatch removal
• Approximation rates for neural networks with general activation functions
• Neural network and regression spline value function approximations for stochastic dynamic programming
• Approximation by series of sigmoidal functions with applications to neural networks
• Risk bounds for mixture density estimation
• A NONPARAMETRIC ESTIMATOR FOR THE COVARIANCE FUNCTION OF FUNCTIONAL DATA
• Learning with generalization capability by kernel methods of bounded complexity
• Convergence of orthogonal greedy algorithm with errors in projectors
• An empirical comparison of the validity of a neural net based multinomial logit choice model to alternative model specifications
• Deviation optimal learning using greedy \(Q\)-aggregation
• Intelligent optimal control of robotic manipulators using neural networks
• Nonparametric neural network estimation of Lyapunov exponents and a direct test for chaos
• Max-product neural network and quasi-interpolation operators activated by sigmoidal functions
• A review on deep learning in medical image reconstruction
• LATTICE OPTION PRICING BY MULTIDIMENSIONAL INTERPOLATION
• Nonparametric estimation of composite functions
• Density estimation through convex combinations of densities: Approximation and estimation bounds
• Dynamic programming and value-function approximation in sequential decision problems: error analysis and numerical results
• An Integral Upper Bound for Neural Network Approximation
• Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018
• Relevance of functional flexibility for heterogeneous sales response models: a comparison of parametric and semi-nonparametric models
• 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
• Input Variable Selection in Neural Network Models

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)