RSCTC '98 Proceedings of the First International Conference on Rough Sets and Current Trends in Computing
Stability Analysis of Oja-RLS Learning Rule
Fundamenta Informaticae
Hi-index | 0.00 |
This paper deals with stability of Oja's symmetric algorithm forestimating the principal component subspace of the input data.Exact conditions are derived for the gain parameter on which thediscrete algorithm remains bounded. The result is extended for anonlinear version of Oja's algorithm.