Name
Title | ||
|---|---|---|
Stability Analysis of Natural Gradient Learning Rules in Complete ICA: A Unifying Perspective |
Abstract | ||
|---|---|---|
This letter deals with the independent component analysis (ICA) problem in the complete case. As appeared recently in the literature, different Riemannian metrics can be defined within the parameter space (i.e., the general linear group), allowing to derive correspondingly various ICA learning rules based on the relative natural gradients (NGs). This letter proposes a general framework to analyze the stability of such learning rules, including the already published study focusing on the Amari's NG approach as a special case thereof. In particular, it is shown that the stability conditions known in the literature still hold in all cases addressed |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/LSP.2006.881520 | IEEE Signal Process. Lett. |
Keywords | Field | DocType |
natural gradient,signal processing,independent component analysis (ica),riemannian metrics,independent component analysis,gradient methods,natural gradient learning rule,stability analysis,stability,ica,general linear group,rule based,parameter space | Natural gradient,Signal processing,Mathematical optimization,Pattern recognition,Stability conditions,General linear group,Artificial intelligence,Independent component analysis,Parameter space,Mathematics,Special case | Journal |
Volume | Issue | ISSN |
14 | 1 | 1070-9908 |
Citations | PageRank | References |
3 | 0.45 | 5 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Stefano Squartini | 1 | 376 | 46.97 |
| Andrea Arcangeli | 2 | 23 | 2.93 |
| Francesco Piazza | 3 | 673 | 100.48 |