Stability Analysis of Oja-RLS Learning Rule
Radosław Sikora , Władysław Skarbek
AbstractIt is shown that the discrete time dynamical system defined by the Oja-RLS algorithm is stable in the closed ring K(0,9/8) – \$\\textbackslash\overline\K\\$ (0,8/9) if only the initial gain β0 is bounded by (2B) −1 , where B = b 2 and b is the bound for the learning sequence. It is rigorously proved that automatically computed gains βn in Oja-RLS scheme converge to zero with the rate 1/n, almost surely.
|Journal series||Fundamenta Informaticae, ISSN 0169-2968|
|Publication indicators||: 2006 = 0.586 (2) - 2007=0.774 (5)|
|Citation count*||6 (2018-06-18)|
* presented citation count is obtained through Internet information analysis and it is close to the number calculated by the Publish or Perish system.