Title :
Learning averages over the lie group of unitary matrices
Author_Institution :
Dipt. di Ing. Biomedica, Elettron. e Telecomun., Univ. Politec. delle Marche, Ancona, Italy
Abstract :
In the present paper, we treat the problem of learning averages out of a set of unitary matrices. We discuss a possible learning technique based on the differential geometrical properties of the Lie group of unitary matrices. We first recall some relevant notions from differential geometry, mainly related to Lie group theory, and then we propose a scheme for learning averages. Some numerical experiments will illustrate the features of the learnt averages.
Keywords :
Lie algebras; Lie groups; differential geometry; learning (artificial intelligence); matrix algebra; Lie group theory; average learning; differential geometrical properties; differential geometry; learning technique; unitary matrices; Biomedical signal processing; Diversity reception; Holographic optical components; Holography; Nonlinear optics; Optical scattering; Particle scattering; Quantum computing; Radar scattering; Sensor arrays;
Conference_Titel :
Neural Networks, 2009. IJCNN 2009. International Joint Conference on
Conference_Location :
Atlanta, GA
Print_ISBN :
978-1-4244-3548-7
Electronic_ISBN :
1098-7576
DOI :
10.1109/IJCNN.2009.5178714