Document Detail


Extended Hamiltonian Learning on Riemannian Manifolds: Theoretical Aspects.
MedLine Citation:
PMID:  21427023     Owner:  NLM     Status:  Publisher    
Abstract/OtherAbstract:
This paper introduces a general theory of extended Hamiltonian (second-order) learning on Riemannian manifolds, as an instance of learning by constrained criterion optimization. The dynamical learning equations are derived within the general framework of extended-Hamiltonian stationary-action principle and are expressed in a coordinate-free fashion. A theoretical analysis is carried out in order to compare the features of the dynamical learning theory with the features exhibited by the gradient-based ones. In particular, gradient-based learning is shown to be an instance of dynamical learning, and the classical gradient-based learning modified by a ``momentum'' term is shown to resemble discrete-time dynamical learning. Moreover, the convergence features of gradient-based and dynamical learning are compared on a theoretical basis. This paper discusses cases of learning by dynamical systems on manifolds of interest in the scientific literature, namely, the Stiefel manifold, the special orthogonal group, the Grassmann manifold, the group of symmetric positive definite matrices, the generalized flag manifold, and the real symplectic group of matrices.
Authors:
Simone Fiori
Related Documents :
1414573 - The effect of free or reduced-price lunches on the self-esteem of middle school students.
11317753 - An open and flexible framework for computer aided surgical training.
19336993 - jsps asian core program on cutting-edge organic chemistry in asia
Publication Detail:
Type:  JOURNAL ARTICLE     Date:  2011-3-22
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  -     ISSN:  1941-0093     ISO Abbreviation:  -     Publication Date:  2011 Mar 
Date Detail:
Created Date:  2011-3-23     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101211035     Medline TA:  IEEE Trans Neural Netw     Country:  -    
Other Details:
Languages:  ENG     Pagination:  -     Citation Subset:  -    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  Recurrent Neural Network for Non-Smooth Convex Optimization Problems with Application to the Identif...
Next Document:  Comments on "State-Feedback Control of Fuzzy Discrete-Event Systems"