Computing the polar decomposition with applications
SIAM Journal on Scientific and Statistical Computing
Independent component analysis, a new concept?
Signal Processing - Special issue on higher order statistics
Natural gradient works efficiently in learning
Neural Computation
Incorporating curvature information into on-line learning
On-line learning in neural networks
Regularizing Flows for Constrained Matrix-Valued Images
Journal of Mathematical Imaging and Vision
Complex independent component analysis of frequency-domain electroencephalographic data
Neural Networks - Special issue: Neuroinformatics
Neural learning by geometric integration of reduced 'rigid-body' equations
Journal of Computational and Applied Mathematics
Functions Preserving Matrix Groups and Iterations for the Matrix Square Root
SIAM Journal on Matrix Analysis and Applications
Quasi-Geodesic Neural Learning Algorithms Over the Orthogonal Group: A Tutorial
The Journal of Machine Learning Research
Nonlinear Complex-Valued Extensions of Hebbian Learning: An Essay
Neural Computation
A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold
Neural Computation
Equivariant adaptive source separation
IEEE Transactions on Signal Processing
Super-exponential methods for blind deconvolution
IEEE Transactions on Information Theory
A theory for learning based on rigid bodies dynamics
IEEE Transactions on Neural Networks
Fast fixed-point neural blind-deconvolution algorithm
IEEE Transactions on Neural Networks
Learning averages over the lie group of unitary matrices
IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
An algorithm to compute averages on matrix Lie groups
IEEE Transactions on Signal Processing
Hi-index | 0.02 |
The aim of this paper is to discuss the class of leap-frog-type neural learning algorithms having the unitary group of matrices as parameter space. In the discussed framework, each step of a learning algorithm computes as an unconstrained learning step followed by a projection step. The present manuscript focuses on projection methods and related implementation issues. Projection methods based on singular/eigenvalue matrix decomposition as well as on QR decomposition are discussed in details. Two possible ways to combine these projection methods, based on projection-operator composition and on geodesic mid-point interpolation, are also discussed and tested numerically.