Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance

DOI10.1162/neco.2007.19.4.1112zbMath1118.68122WikidataQ51920784 ScholiaQ51920784MaRDI QIDQ3440433

Sumio Watanabe, Shinichi Nakajima

Publication date: 22 May 2007

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

Full work available at URL: https://doi.org/10.1162/neco.2007.19.4.1112

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

68M20: Performance evaluation, queueing, and scheduling in the context of computer systems

Cites Work

• Stochastic complexity and modeling
• The strong limits of random matrix spectra for sample matrices of independent elements
• Estimating the dimension of a model
• Weights of \(\overline{\chi}^2\) distribution for smooth or piecewise smooth cone alternatives
• Likelihood ratio of unidentifiable models and multilayer neural networks
• Tail probabilities of the maxima of multilinear forms and their applications.
• Stochastic complexities of reduced rank regression in Bayesian estimation
• Algebraic Analysis for Nonidentifiable Learning Machines
• Online Model Selection Based on the Variational Bayes
• On the Problem in Model Selection of Neural Network Regression in Overrealizable Scenario
• Testing in locally conic models, and application to mixture models
• Learning Coefficients of Layered Models When the True Distribution Mismatches the Singularities
• A new look at the statistical model identification