Neural learning by geometric integration of reduced `rigid-body' equations

DOI10.1016/J.CAM.2004.02.007zbMATH Open1082.68095OpenAlexW2118708484MaRDI QIDQ704191FDOQ704191

Elena Celledoni, S. Fiori

Publication date: 13 January 2005

Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cam.2004.02.007

Recommendations

• Quasi-geodesic neural learning algorithms over the orthogonal group: a tutorial
• A theory for learning by weight flow on Stiefel-Grassman manifold
• Complex-weighted one-unit `rigid-bodies' learning rule for independent component analysis
• Computational Science and Its Applications – ICCSA 2004
• Stability and Convergence of Principal Component Learning Algorithms

zbMATH Keywords

component analysisorthonormal learning of linear neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Independent component analysis, a new concept?
• Title not available (Why is that?)
• The Geometry of Algorithms with Orthogonality Constraints
• Title not available (Why is that?)
• Principal component analysis in linear systems: Controllability, observability, and model reduction
• Title not available (Why is that?)
• Approximating the exponential from a Lie algebra to a Lie group
• Title not available (Why is that?)
• Computation of orthonormal factors for fundamental solution matrices
• Dynamical systems that sort lists, diagonalize matrices, and solve linear programming problems
• On the implementation of Lie group methods on the Stiefel manifold
• Exponentiated gradient versus gradient descent for linear predictors
• A recurrence among the elements of functions of triangular matrices
• On the Kunneth Formula and Functorial Dependence in Algebraic Topology
• Methods for the approximation of the matrix exponential in a Lie-algebraic setting
• Computing Lyapunov exponents on a Stiefel manifold
• Gradient systems in view of information geometry
• Blind separation of circularly distributed sources by neural extended APEX algorithm
• A theory for learning by weight flow on Stiefel-Grassman manifold
• Entropy optimization by the PFANN network: application to blind source separation

Cited In (10)

• Complex-weighted one-unit `rigid-bodies' learning rule for independent component analysis
• Blind deconvolution by a Newton method on the non-unitary hypersphere
• Generalized polar coordinates on Lie groups and numerical integrators
• An introduction to Lie group integrators - basics, new developments and applications
• Nonlinear Complex-Valued Extensions of Hebbian Learning: An Essay
• Nonlinear damped oscillators on Riemannian manifolds: fundamentals
• Descent methods for optimization on homogeneous manifolds
• Auto-regressive moving-average discrete-time dynamical systems and autocorrelation functions on real-valued Riemannian matrix manifolds
• A theory for learning by weight flow on Stiefel-Grassman manifold
• Structure-preserving deep learning

This page was built for publication: Neural learning by geometric integration of reduced `rigid-body' equations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q704191)