Abstract | ||
---|---|---|
The present manuscript treats the problem of adapting a neural signal processing system whose parameters belong to a curved manifold, which is assumed to possess the structure of a Lie group. Neural system parameter adapting is effected by optimizing a system performance criterion. Riemannian-gradient-based optimization is suggested, which cannot be performed by standard additive stepping because of the curved nature of the parameter space. Retraction-based stepping is discussed, instead, along with a companion stepsize-schedule selection procedure. A case-study of learning by optimization of a non-quadratic criterion is discussed in detail. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1016/j.neunet.2008.09.009 | Neural Networks |
Keywords | Field | DocType |
lie groups,curved nature,manifold retraction,riemannian-gradient-based optimization,curved manifold,system performance criterion,lie-group-type neural system,manifold retractions,companion stepsize-schedule selection procedure,neural learning theory,neural signal processing systems,neural signal processing system,non-quadratic criterion,neural system parameter adapting,parameter space,lie group,learning theory,signal processing,system performance | Gradient method,Signal processing,Topology,Lie group,Mathematical optimization,Curvature,Algorithm,Type theory,Parameter space,Artificial neural network,Mathematics,Manifold | Journal |
Volume | Issue | ISSN |
21 | 10 | 0893-6080 |
Citations | PageRank | References |
12 | 0.82 | 8 |
Authors | ||
1 |
Name | Order | Citations | PageRank |
---|---|---|---|
Simone Fiori | 1 | 494 | 52.86 |