A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold

DOI10.1162/089976601750265036zbMath0982.68111OpenAlexW2169736182MaRDI QIDQ2746421

Simone Fiori

Publication date: 10 October 2001

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

Full work available at URL: https://doi.org/10.1162/089976601750265036

zbMATH Keywords

neural network learningmultilayer perceptron-like networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (8)

Generalized neural networks for spectral analysis: dynamics and Liapunov functions ⋮ Preserving geometric properties of the exponential matrix by block Krylov subspace methods ⋮ Blind Separation of Positive Sources by Globally Convergent Gradient Search ⋮ Lie-group-type neural system learning by manifold retractions ⋮ Nonlinear Complex-Valued Extensions of Hebbian Learning: An Essay ⋮ Neural learning by geometric integration of reduced `rigid-body' equations ⋮ A fast and adaptive ICA algorithm with its application to fetal electrocardiogram extraction ⋮ Descent methods for optimization on homogeneous manifolds

Cites Work

• Global optimization and stochastic differential equations
• Independent component analysis by general nonlinear Hebbian-like learning rules
• Neural networks for blind separation with unknown number of sources
• Independent component analysis, a new concept?
• Dynamical systems that sort lists, diagonalize matrices, and solve linear programming problems
• Richtungsfelder und Fernparallelismus in \(n\)-dimensionalen Mannigfaltigkeiten
• The Geometry of Algorithms with Orthogonality Constraints
• HIGH-ORDER CONTRASTS FOR SELF-ADAPTIVE SOURCE SEPARATION

This page was built for publication: A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold