Lie-group-type neural system learning by manifold retractions

DOI10.1016/j.neunet.2008.09.009zbMath1254.92009WikidataQ51864644 ScholiaQ51864644MaRDI QIDQ1932122

Simone Fiori

Publication date: 17 January 2013

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

Full work available at URL: https://doi.org/10.1016/j.neunet.2008.09.009

zbMATH Keywords

Lie groups; manifold retractions; neural learning theory; neural signal processing systems

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

92C20: Neural biology

94A12: Signal theory (characterization, reconstruction, filtering, etc.)

Related Items

A possible neural representation of mathematical group structures, Sympnets: intrinsic structure-preserving symplectic networks for identifying Hamiltonian systems, Averaging on manifolds by embedding algorithm

Uses Software

• FastICA
• ICALAB

Cites Work

• Unnamed Item
• Minimizing a differentiable function over a differential manifold
• Runge-Kutta methods on Lie groups
• Trust-region methods on Riemannian manifolds
• A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold
• Newton's method on Riemannian manifolds and a geometric model for the human spine
• A Class of Intrinsic Schemes for Orthogonal Integration
• Optimization algorithms exploiting unitary constraints
• A Study on Neural Learning on Manifold Foliations: The Case of the Lie Group SU(3)
• The Gradient Projection Method Along Geodesics
• Riemannian geometry