On the Problem in Model Selection of Neural Network Regression in Overrealizable Scenario

DOI10.1162/089976602760128090zbMATH Open1010.68115OpenAlexW1974755789WikidataQ74614436 ScholiaQ74614436MaRDI QIDQ3149529FDOQ3149529

Katsuyuki Hagiwara

Publication date: 25 September 2002

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/089976602760128090

Recommendations

• Radial basis function networks: Generalization in over-realizable and unrealizable scenarios
• scientific article; zbMATH DE number 17222
• On the generalization problem
• Publication:4955300
• Relation between weight size and degree of over-fitting in neural network regression

zbMATH Keywords

radial basis functionsstatistical model selection of neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Estimating the dimension of a model
• Testing the order of a model using locally conic parametrization: Population mixtures and stationary ARMA processes
• Fitting autoregressive models for prediction
• Stochastic complexity and modeling
• Algebraic analysis for nonidentifiable learning machines
• Testing in locally conic models, and application to mixture models

Cited In (13)

• Learning Coefficients of Layered Models When the True Distribution Mismatches the Singularities
• Relation between weight size and degree of over-fitting in neural network regression
• Search for a possible variation of the fine structure constant
• Dynamics of Learning Near Singularities in Layered Networks
• Asymptotic analysis of Bayesian generalization error with Newton diagram
• Quantum information criteria for model selection in quantum state estimation
• On the Asymptotic Distribution of the Least-Squares Estimators in Unidentifiable Models
• Equations of states in singular statistical estimation
• Parameter Identifiability in Statistical Machine Learning: A Review
• Tutorial on brain-inspired computing. II: Multilayer perceptron and natural gradient learning
• Asymptotics for regression models under loss of identifiability
• Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance
• Improving Generalization Performance of Natural Gradient Learning Using Optimized Regularization by NIC

This page was built for publication: On the Problem in Model Selection of Neural Network Regression in Overrealizable Scenario

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3149529)