Likelihood ratio of unidentifiable models and multilayer neural networks

DOI10.1214/AOS/1056562464zbMath1032.62020OpenAlexW2086236873MaRDI QIDQ1412367

Kenji Fukumizu

Publication date: 10 November 2003

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aos/1056562464

zbMATH Keywords

likelihood ratiomultilayer neural networkslocally conic modelunidentifiable model

Mathematics Subject Classification ID

Asymptotic properties of parametric estimators (62F12) Point estimation (62F10) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (12)

Relation between weight size and degree of over-fitting in neural network regression ⋮ Parameter Identifiability in Statistical Machine Learning: A Review ⋮ Difficulty of Singularity in Population Coding ⋮ Asymptotics for regression models under loss of identifiability ⋮ A goodness-of-fit test based on neural network sieve estimators ⋮ Density estimation by the penalized combinatorial method ⋮ Tutorial on brain-inspired computing. II: Multilayer perceptron and natural gradient learning ⋮ Consistent estimation of the architecture of multilayer perceptrons. ⋮ Dynamics of Learning Near Singularities in Layered Networks ⋮ EDI-Graphic: A Tool To Study Parameter Discrimination and Confirm Identifiability in Black-Box Models, and to Select Data-Generating Machines ⋮ Estimation and tests in finite mixture models of nonparametric densities ⋮ Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance

Cites Work

• Testing the order of a model using locally conic parametrization: Population mixtures and stationary ARMA processes
• ASYMPTOTIC DISTRIBUTIONS OF LIKELIHOOD RATIOS FOR OVERPARAMETRIZED ARMA PROCESSES
• Testing in locally conic models, and application to mixture models
• The likelihood ratio test for the number of components in a mixture with Markov regime
• On the Assumptions Used to Prove Asymptotic Normality of Maximum Likelihood Estimates
• Note on the Consistency of the Maximum Likelihood Estimate
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Likelihood ratio of unidentifiable models and multilayer neural networks