Learning Coefficients of Layered Models When the True Distribution Mismatches the Singularities

DOI10.1162/089976603765202640zbMath1085.68138OpenAlexW2134101287MaRDI QIDQ4816944

Sumio Watanabe, Shun-ichi Amari

Publication date: 14 September 2004

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

Full work available at URL: https://doi.org/10.1162/089976603765202640

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (6)

Asymptotic analysis of singular likelihood ratio of normal mixture by Bayesian learning theory for testing homogeneity ⋮ Recent advances in algebraic geometry and Bayesian statistics ⋮ Parameter Identifiability in Statistical Machine Learning: A Review ⋮ Equations of states in singular statistical estimation ⋮ Dynamics of Learning Near Singularities in Layered Networks ⋮ Variational Bayes Solution of Linear Neural Networks and Its Generalization Performance

Cites Work

• Resolution of singularities of an algebraic variety over a field of characteristic zero. I
• Algebraic Analysis for Nonidentifiable Learning Machines
• On the Problem in Model Selection of Neural Network Regression in Overrealizable Scenario
• Resolution of Singularities and Division of Distributions

This page was built for publication: Learning Coefficients of Layered Models When the True Distribution Mismatches the Singularities