Singularities Affect Dynamics of Learning in Neuromanifolds

DOI10.1162/089976606776241002zbMath1092.68636OpenAlexW2001689396MaRDI QIDQ5467068

Tomoko Ozeki, Hyeyoung Park, Shun-ichi Amari

Publication date: 23 May 2006

Full work available at URL: https://doi.org/10.1162/089976606776241002

zbMATH Keywords

statistical manifolds

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (12)

Statistical mechanical analysis of learning dynamics of two-layer perceptron with multiple output units ⋮ Second-order stagewise backpropagation for Hessian-matrix analyses and investigation of negative curvature ⋮ Dynamics of learning near singularities in radial basis function networks ⋮ Natural Gradient Learning Algorithms for RBF Networks ⋮ Learning Dynamics of a Single Polar Variable Complex-Valued Neuron ⋮ Parameter Identifiability in Statistical Machine Learning: A Review ⋮ Asymptotics for regression models under loss of identifiability ⋮ Dynamics of Learning in MLP: Natural Gradient and Singularity Revisited ⋮ Dying ReLU and Initialization: Theory and Numerical Examples ⋮ Unnamed Item ⋮ Equations of states in singular statistical estimation ⋮ Analysis of artificial neural network learning near temporary minima: a fuzzy logic approach

This page was built for publication: Singularities Affect Dynamics of Learning in Neuromanifolds