Title :
Energy function for the one-unit Oja algorithm
Author :
Zhang, Qingfu ; Leung, Yiu-Wing
Author_Institution :
Dept. of Comput., Changsha Inst. of Technol., China
fDate :
9/1/1995 12:00:00 AM
Abstract :
The one-unit Oja algorithm plays a very important role in the study of principal component analysis neural networks. In this paper, we propose an energy function whose steepest descent direction (i.e., negative gradient direction) is the same as the average evolution direction of the one-unit Oja algorithm, and the energy function has two global minimal points corresponding to the two converged points of the one-unit Oja algorithm and it has no other local minimal points
Keywords :
convergence of numerical methods; covariance matrices; neural nets; optimisation; average evolution direction; covariance matrix; energy function; global minimal points; negative gradient direction; neural networks; one-unit Oja algorithm; principal component analysis; steepest descent direction; Approximation algorithms; Convergence; Covariance matrix; Least squares approximation; Lyapunov method; Mean square error methods; Neural networks; Packaging; Principal component analysis; Stochastic processes;
Journal_Title :
Neural Networks, IEEE Transactions on
