Abstract | ||
---|---|---|
The present paper aims at introducing a novel procedure for designing an averaging algorithm for a committee of learning machines under the assumption that the machines share a common parameter-space, namely, the group of special orthogonal matrices SO(p). The averaging procedure inputs the patterns learnt by the machines in the committee and outputs a mean-matrix that represents an average of machines' patterns. Since the space SO(p) is a curved manifold, averaging does not carry on the usual (Euclidean) meaning and should be designed on the basis of the parameter-space's geometric properties. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1109/ISCAS.2008.4541881 | Seattle, WA |
Keywords | Field | DocType |
differential geometry,learning (artificial intelligence),matrix algebra,averaging method,geometric properties,learning machines,special orthogonal matrices,special-orthogonal-group machines | Orthogonal matrix,Algebra,Computer science,Control theory,Matrix algebra,Algorithm,Differential geometry,Euclidean geometry,Orthogonal group,Manifold | Conference |
ISSN | ISBN | Citations |
0271-4302 | 978-1-4244-1684-4 | 0 |
PageRank | References | Authors |
0.34 | 4 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Fiori | 1 | 494 | 52.86 |
T. Tanaka | 2 | 638 | 95.91 |