Title | ||
---|---|---|
Mixed maps for learning a Kolmogoroff-Nagumo-type average element on the compact Stiefel manifold |
Abstract | ||
---|---|---|
The present research work proposes a new fast fixed-point average-value learning algorithm on the compact Stiefel manifold based on a mixed retraction/lifting pair. Numerical comparisons between fixed-point algorithms based on the proposed non-associated retraction/lifting map pair and two associated retraction/lifting pairs confirm that the averaging algorithm based on a combination of mixed maps is remarkably less computationally demanding than the same averaging algorithm based on any of the constituent associated retraction/lifting pairs. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICASSP.2014.6854457 | Acoustics, Speech and Signal Processing |
Keywords | Field | DocType |
learning (artificial intelligence),Kolmogoroff-Nagumo-type average element learning,compact Stiefel manifold,fast fixed-point average-value learning algorithm,mixed map combination,mixed retraction-lifting pair,nonassociated retraction-lifting map pair,Compact Stiefel manifold,Empirical averaging,Fixed-point iteration,Kolmogoroff-Nagumo mean,Manifold retraction/lifting maps | Mathematical optimization,Stiefel manifold,Manifold alignment,Mathematics | Conference |
ISSN | Citations | PageRank |
1520-6149 | 1 | 0.36 |
References | Authors | |
10 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Fiori | 1 | 494 | 52.86 |
Tetsuya Kaneko | 2 | 1 | 0.36 |
T. Tanaka | 3 | 638 | 95.91 |