Stability analysis of Oja-RLS learning rule

• Autorzy: Sikora R. , Skarbek W.
• Języki publikacji: EN

Abstrakty

EN

It is shown that the discrete time dynamical system defined by the Oja-RLS algorithm is stable in the closed ring K(0,9/8) - K(0,8/9) if only the initial gain B0 is bounded by (2B)-1, where B=b2 and b is the bound for the learning sequence. It is rigorously proved that automatically computed gains Bn in Oja-RLS scheme converge to zero with the rate 1/n, almost surely.

Słowa kluczowe

EN

KLT transform; principal component analysis; OJA-RLS learning scheme; stability of neural algorithm

• Wydawca: IOS Press
• Czasopismo: Fundamenta Informaticae
• Rocznik: 1998
• Tom: Vol. 34, nr 4
• Strony: 441--453
• Opis fizyczny: bibliogr. 15 poz.

Twórcy

autor

Sikora R.

autor

Skarbek W.

• Multimedia Laboratory, Faculty of Electronics and Information Technology, Warsaw University of Technology, Nowowiejska 15/19, 00-665 Warsaw, Poland