Matrix High Dimensional Model Representation (MHDMR) with the Weight Matrices Generated by Subspace Construction

Tuna S., Demiralp M.

International Conference on Numerical Analysis and Applied Mathematics (ICNAAM), Halkidiki, Greece, 19 - 25 September 2011, vol.1389 identifier identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: 1389
  • Doi Number: 10.1063/1.3637829
  • City: Halkidiki
  • Country: Greece
  • Istanbul Technical University Affiliated: Yes

Abstract

High Dimensional Model Representation(HDMR) is one of the well-known decomposition methods to partition multivariate functions or given data sets. Although HDMR and its varieties can handle their tasks successfully, it is never revived that it can also be utilized for matrices, function argumented matrices can, until Demiralp and his group has started to work on this topic. After some valuable studies, a new HDMR type has just come forward: Matrix HDMR(MHDMR). In this paper, MHDMR and its features will be introduced.