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

Authors:
Simone Fiori
Affiliations:
Dipartimento di Elettronica, Intelligenza Artificiale e Telecomunicazioni, Facolt di Ingegneria, Universit Politecnica delle Marche, I-60131 Ancona, Italy. fiorideit.univpm.it
Venue:
Neural Computation
Year:
2008

Citing 9
Cited 6

Natural gradient works efficiently in learning

Neural Computation
Approximating the exponential from a Lie algebra to a Lie group

Mathematics of Computation
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
Editorial: Geometrical methods in neural networks and learning

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

Neurocomputing
The geometry of prior selection

Neurocomputing
Three-transmit-antenna space-time codes based on SU(3)

IEEE Transactions on Signal Processing - Part I
Equivariant adaptive source separation

IEEE Transactions on Signal Processing

Natural Conjugate Gradient on Complex Flag Manifolds for Complex Independent Subspace Analysis

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Lie-group-type neural system learning by manifold retractions

Neural Networks
Conjugate gradient algorithm for optimization under unitary matrix constraint

Signal Processing
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
Periodic activation function and a modified learning algorithm for the multivalued neuron

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Learning on differential manifolds may involve the optimization of a function of many parameters. In this letter, we deal with Riemannian-gradient-based optimization on a Lie group, namely, the group of unitary unimodular matrices SU(3). In this special case, subalgebras of the associated Lie algebra su(3) may be individuated by computing pair-wise Gell-Mann matrices commutators. Subalgebras generate subgroups of a Lie group, as well as manifold foliation. We show that the Riemannian gradient may be projected over tangent structures to foliation, giving rise to foliation gradients. Exponentiations of foliation gradients may be computed in closed forms, which closely resemble Rodriguez forms for the special orthogonal group SO(3). We thus compare optimization by Riemannian gradient and foliation gradients.