scientific article; zbMATH DE number 17222

zbMATH Open0739.62001MaRDI QIDQ3973919FDOQ3973919

Authors: Andrew R. Barron 

Publication date: 26 June 1992

Title of this publication is not available (Why is that?)

Recommendations

• Practical complexity control in multilayer perceptrons
• Bounds on the complexity of neural‐network models and comparison with linear methods
• Complexity of learning in artificial neural networks
• Complexity and neural networks
• Neural networks and complexity theory
• Complexity matching in neural networks
• scientific article; zbMATH DE number 67614
• Publication:3484350
• Estimates of Data Complexity in Neural-Network Learning
• Approximation by Fully Complex Multilayer Perceptrons

zbMATH Keywords

model selectionartificial neural networksconsistencyparameter estimation errorrates of convergencepolynomial regressionapproximation errorrisk boundsstatistical estimation of functionscomplexity of modelscomplexity regularization criteriaindex of resolvabilityminimum description-length criterianear asymptotic optimality

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Density estimation (62G07) Asymptotic properties of nonparametric inference (62G20) Applications of statistics (62P99)

Cited In (47)

• Risk bounds for model selection via penalization
• Model selection in nonparametric regression
• Analysis of the rate of convergence of fully connected deep neural network regression estimates with smooth activation function
• Interpreting neural-network results: a simulation study.
• Smooth discrimination analysis
• Collocation approximation by deep neural ReLU networks for parametric and stochastic PDEs with lognormal inputs
• Model selection in reinforcement learning
• How well can a regression function be estimated if the distribution of the (random) design is concentrated on a finite set?
• Functional aggregation for nonparametric regression.
• Analysis of the rate of convergence of least squares neural network regression estimates in case of measurement errors
• Discriminatively regularized least-squares classification
• Quasicycles revisited: apparent sensitivity to initial conditions
• Density estimation by the penalized combinatorial method
• A new method for estimation and model selection: \(\rho\)-estimation
• Nonlinear orthogonal series estimates for random design regression
• Self-regulated complexity in neural networks
• Adaptive estimation in autoregression or \(\beta\)-mixing regression via model selection
• On deep learning as a remedy for the curse of dimensionality in nonparametric regression
• Neural networks and logistic regression: Part I
• On the mathematical foundations of learning
• Approximation and learning by greedy algorithms
• On the Problem in Model Selection of Neural Network Regression in Overrealizable Scenario
• Deep ReLU neural network approximation in Bochner spaces and applications to parametric PDEs
• Hybrid machine learning model for continuous microarray time series
• A multi-loss super regression learner (MSRL) with application to survival prediction using proteomics
• Title not available (Why is that?)
• On estimation of surrogate models for multivariate computer experiments
• Data-adaptive estimation of the treatment-specific mean
• Synchronous Boltzmann machines can be universal approximators
• Nonparametric estimation of low rank matrix valued function
• Optimal aggregation of classifiers in statistical learning.
• About the non-asymptotic behaviour of Bayes estimators
• Ridgelets: estimating with ridge functions
• On the rate of convergence of fully connected deep neural network regression estimates
• Information-theoretic determination of minimax rates of convergence
• Nonasymptotic bounds on the \(L_{2}\) error of neural network regression estimates
• Model selection based on minimum description length
• Title not available (Why is that?)
• Multiclass classification with potential function rules: margin distribution and generalization
• Suboptimal behavior of Bayes and MDL in classification under misspecification
• Title not available (Why is that?)
• Time-penalised trees (\texttt{TpT}): introducing a new tree-based data mining algorithm for time-varying covariates
• Gaussian model selection with an unknown variance
• Deep ReLU networks and high-order finite element methods
• Theory of Classification: a Survey of Some Recent Advances
• Model selection by bootstrap penalization for classification
• Deep learning in high dimension: neural network expression rates for generalized polynomial chaos expansions in UQ

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3973919)