Approximation by neural networks and learning theory

DOI10.1016/J.JCO.2005.09.001zbMATH Open1156.68541OpenAlexW2044675413MaRDI QIDQ2489152FDOQ2489152

Authors: Vitaly Maiorov 

Publication date: 16 May 2006

Published in: Journal of Complexity (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jco.2005.09.001

Recommendations

• Learning theory and approximation by neural networks
• scientific article; zbMATH DE number 35425
• Hardness results for neural network approximation problems
• On the near optimality of the stochastic approximation of smooth functions by neural networks
• scientific article; zbMATH DE number 2087696

zbMATH Keywords

EntropyNeural networksLearning theoryStochastic approximation

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Stochastic approximation (62L20) Neural nets and related approaches to inference from stochastic processes (62M45) Neural networks for/in biological studies, artificial life and related topics (92B20)

Cites Work

• Regularization networks and support vector machines
• Ten Lectures on Wavelets
• On the mathematical foundations of learning
• Title not available (Why is that?)
• Title not available (Why is that?)
• Sharper bounds for Gaussian and empirical processes
• A distribution-free theory of nonparametric regression
• Local Rademacher complexities
• The Radon transform
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension
• Neural Network Learning
• PIECEWISE-POLYNOMIAL APPROXIMATIONS OF FUNCTIONS OF THE CLASSES $ W_{p}^{\alpha}$
• Lower bounds for approximation by MLP neural networks
• Pseudo-dimension and entropy of manifolds formed by affine-invariant dictionary
• Lower bounds for multivariate approximation by affine-invariant dictionaries
• The sizes of compact subsets of Hilbert space and continuity of Gaussian processes
• Title not available (Why is that?)
• The entropy in learning theory. Error estimates
• Title not available (Why is that?)
• Entropy and the combinatorial dimension
• Necessary and Sufficient Conditions for the Uniform Convergence of Means to their Expectations
• Relaxation in greedy approximation
• On the value of partial information for learning from examples
• Title not available (Why is that?)
• Title not available (Why is that?)
• On the near optimality of the stochastic approximation of smooth functions by neural networks

Cited In (50)

• Learning \(C^2\) and Hölder functions
• Asymptotics of Reinforcement Learning with Neural Networks
• Application of adjoint operators to neural learning
• Title not available (Why is that?)
• Geometric Rates of Approximation by Neural Networks
• Title not available (Why is that?)
• Deep Neural Network Approximation Theory
• On approximate learning by multi-layered feedforward circuits
• Approximation spaces of deep neural networks
• Approximation theorems for a family of multivariate neural network operators in Orlicz-type spaces
• Title not available (Why is that?)
• Title not available (Why is that?)
• Approximation results in Orlicz spaces for sequences of Kantorovich MAX-product neural network operators
• Using Prior Information to Improve the Approximation Performances of Neural Networks
• Almost optimal estimates for approximation and learning by radial basis function networks
• Title not available (Why is that?)
• Convergence for a family of neural network operators in Orlicz spaces
• Approximation by max-product neural network operators of Kantorovich type
• Title not available (Why is that?)
• Voronovskaja type theorems and high-order convergence neural network operators with sigmoidal functions
• Model reduction by CPOD and Kriging: application to the shape optimization of an intake port
• THE NEWTON NEURAL NET: A NEW APPROXIMATING NETWORK
• Approximating smooth and sparse functions by deep neural networks: optimal approximation rates and saturation
• Pointwise and uniform approximation by multivariate neural network operators of the max-product type
• Learning Theory
• Quantitative estimates involving \(K\)-functionals for neural network-type operators
• Constrained proper orthogonal decomposition based on QR-factorization for aerodynamical shape optimization
• Neural network operators: constructive interpolation of multivariate functions
• Approximation methods for supervised learning
• Learning and approximating piecewise smooth functions by deep sigmoid neural networks
• Interpolation and rates of convergence for a class of neural networks
• Title not available (Why is that?)
• Some problems in the theory of ridge functions
• Approximation of classifiers by deep perceptron networks
• Approximation by sums of ridge functions with fixed directions
• Approximation rates for neural networks with general activation functions
• Sample complexity bounds for the local convergence of least squares approximation
• Approximation by neural networks with weights varying on a finite set of directions
• Local approximation on artificial neural networks
• Neural nets learning as an inverse problem
• Can neural networks extrapolate? Discussion of a theorem by Pedro Domingos
• Max-product neural network and quasi-interpolation operators activated by sigmoidal functions
• Learning sparse and smooth functions by deep sigmoid nets
• Convergence results for a family of Kantorovich max-product neural network operators in a multivariate setting
• Scalable learning method for feedforward neural networks using minimal-enclosing-ball approximation
• Training neural networks with noisy data as an ill-posed problem
• Saturation classes for MAX-product neural network operators activated by sigmoidal functions
• Title not available (Why is that?)
• Title not available (Why is that?)
• Learning theory and approximation by neural networks

This page was built for publication: Approximation by neural networks and learning theory

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2489152)