Abstract | ||
---|---|---|
This paper deals with learning by natural-gradient optimization on noncompact manifolds. In a Riemannian manifold, the calculation of entities such as the closed form of geodesic curves over noncompact manifolds might be infeasible. For this reason, it is interesting to study the problem of learning by optimization over noncompact manifolds endowed with pseudo-Riemannian metrics, which may give rise to tractable calculations. A general theory for natural-gradient-based learning on noncompact manifolds as well as specific cases of interest of learning are discussed. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/TNN.2010.2043445 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
natural gradient,specific case,noncompact manifold,riemannian manifold,natural-gradient-based learning,geodesic curve,pseudo-riemannian metrics,general theory,natural-gradient optimization,closed form,paper deal,symmetric matrices,artificial intelligence,learning artificial intelligence,algorithms,telecommunications,geometry | Matrix algebra,Riemannian manifold,Matrix (mathematics),Artificial intelligence,Manifold,Natural gradient,Combinatorics,Pattern recognition,Pure mathematics,Symmetric matrix,Ricci-flat manifold,Geodesic,Mathematics | Journal |
Volume | Issue | ISSN |
21 | 5 | 1941-0093 |
Citations | PageRank | References |
7 | 0.63 | 7 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Fiori | 1 | 494 | 52.86 |