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

Authors:
Simone Fiori
Affiliations:
Neural Networks and Adaptive System Research Group, Department of Industrial Engineering, University of Perugia, Italy
Venue:
Neural Computation
Year:
2001

Citing 20
Cited 25

Original Contribution: Blind separation of sources: A nonlinear neural algorithm

Neural Networks
Modified Hebbian learning for curve and surface fitting

Neural Networks
Independent component analysis, a new concept?

Signal Processing - Special issue on higher order statistics
Nonlinear higher-order statistical decorrelation by volume-conserving neural architectures

Neural Networks
An information-maximization approach to blind separation and blind deconvolution

Neural Computation
Adaptive online learning algorithms for blind separation: maximum entropy and minimum mutual information

Neural Computation
Independent component analysis by general nonlinear Hebbian-like learning rules

Signal Processing - Special issue on neural networks
Natural gradient works efficiently in learning

Neural Computation
A unified algorithm for principal and minor components extraction

Neural Networks
The Geometry of Algorithms with Orthogonality Constraints

SIAM Journal on Matrix Analysis and Applications
Natural gradient learning for over- and under-complete bases in ICA

Neural Computation
Neural Networks for Optimization and Signal Processing

Neural Networks for Optimization and Signal Processing
Application of the MEC Network to Principal Component Analysis and Source Separation

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Neural Network Based Processing for Smart Sensors Arrays

ICANN '97 Proceedings of the 7th International Conference on Artificial Neural Networks
Discriminant Pattern Recognition Using Transformation-Invariant Neurons

Neural Computation
Tracking directions-of-arrival with invariant subspace updating

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 05
Sparse basis selection, ICA, and majorization: towards a unified perspective

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02
Statistical independence and novelty detection with information preserving nonlinear maps

Neural Computation
Projection approximation subspace tracking

IEEE Transactions on Signal Processing
Equivariant adaptive source separation

IEEE Transactions on Signal Processing

Complex-Weighted One-Unit ‘Rigid-Bodies’ Learning Rule for Independent Component Analysis

Neural Processing Letters
Hybrid independent component analysis by adaptive LUT activation function neurons

Neural Networks
Neural independent component analysis by 'maximum-mismatch' learning principle

Neural Networks
Optimal Linear Representations of Images for Object Recognition

IEEE Transactions on Pattern Analysis and Machine Intelligence
Blind separation of positive sources by globally convergent gradient search

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

Journal of Computational and Applied Mathematics
Overview of independent component analysis technique with an application to synthetic aperture radar (SAR) imagery processing

Neural Networks - 2003 Special issue: Neural network analysis of complex scientific data: Astronomy and geosciences
Nonlinear Complex-Valued Extensions of Hebbian Learning: An Essay

Neural Computation
Fixed-point neural independent component analysis algorithms on the orthogonal group

Future Generation Computer Systems
Gaussianization: An Efficient Multivariate Density Estimation Technique for Statistical Signal Processing

Journal of VLSI Signal Processing Systems
Leap-frog-type learning algorithms over the Lie group of unitary matrices

Neurocomputing
Modified Modulated Hebb-Oja Learning Rule: A Method for Biologically Plausible Principal Component Analysis

Neural Information Processing
Lie-group-type neural system learning by manifold retractions

Neural Networks
Descent methods for optimization on homogeneous manifolds

Mathematics and Computers in Simulation
Fixed-point neural independent component analysis algorithms on the orthogonal group

Future Generation Computer Systems
An algorithm to compute averages on matrix Lie groups

IEEE Transactions on Signal Processing
Learning algorithms utilizing quasi-geodesic flows on the Stiefel manifold

Neurocomputing
Tools for application-driven linear dimension reduction

Neurocomputing
Geometrical methods for non-negative ICA: Manifolds, Lie groups and toral subalgebras

Neurocomputing
Complex independent component analysis by entropy bound minimization

IEEE Transactions on Circuits and Systems Part I: Regular Papers
Independent component analysis by entropy bound minimization

IEEE Transactions on Signal Processing
A class of learning algorithms for principal component analysis based on time-oriented hierarchical method

MUSP'06 Proceedings of the 6th WSEAS international conference on Multimedia systems & signal processing
A closed-form solution to the problem of averaging over the lie group of special orthogonal matrices

ISNN'10 Proceedings of the 7th international conference on Advances in Neural Networks - Volume Part I
Monotonic convergence of a nonnegative ICA algorithm on stiefel manifold

ICONIP'06 Proceedings of the 13 international conference on Neural Information Processing - Volume Part I
Recognition of two-dimensional representation of urban environment for autonomous flying agents

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	0.01

Visualization

Abstract

Recently we introduced the concept of neural network learning on Stiefel-Grassman manifold for multilayer perceptron-like networks. Contributions of other authors have also appeared in the scientific literature about this topic. This article presents a general theory for it and illustrates how existing theories may be explained within the general framework proposed here.