Lie-group-type neural system learning by manifold retractions

Authors:
Simone Fiori
Affiliations:
Dipartimento di Ingegneria Biomedica, Elettronica, e Telecomunicazioni (DIBET), Universití Politecnica delle Marche, Via Brecce Bianche, I-60131 Ancona, Italy
Venue:
Neural Networks
Year:
2008

Citing 8
Cited 1

A Class of Intrinsic Schemes for Orthogonal Integration

SIAM Journal on Numerical Analysis
Quasi-Geodesic Neural Learning Algorithms Over the Orthogonal Group: A Tutorial

The Journal of Machine Learning Research
A Theory for Learning by Weight Flow on Stiefel-Grassman Manifold

Neural Computation
Trust-Region Methods on Riemannian Manifolds

Foundations of Computational Mathematics
A study on neural learning on manifold foliations: The case of the lie group su(3)

Neural Computation
Learning algorithms utilizing quasi-geodesic flows on the Stiefel manifold

Neurocomputing
Optimization algorithms exploiting unitary constraints

IEEE Transactions on Signal Processing
Equivariant adaptive source separation

IEEE Transactions on Signal Processing

Learning by natural gradient on noncompact matrix-type pseudo-Riemannian manifolds

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.03

Visualization

Abstract

The present manuscript treats the problem of adapting a neural signal processing system whose parameters belong to a curved manifold, which is assumed to possess the structure of a Lie group. Neural system parameter adapting is effected by optimizing a system performance criterion. Riemannian-gradient-based optimization is suggested, which cannot be performed by standard additive stepping because of the curved nature of the parameter space. Retraction-based stepping is discussed, instead, along with a companion stepsize-schedule selection procedure. A case-study of learning by optimization of a non-quadratic criterion is discussed in detail.