Global Convergence of a PCA Learning Algorithm with a Constant Learning Rate

Authors:
Jian Cheng Lv;Zhang Yi
Affiliations:
Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, P.R. China;Computational Intelligence Laboratory, School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu 610054, P.R. China
Venue:
Computers & Mathematics with Applications
Year:
2006

Citing 17
Cited 0

Original Contribution: Principal components, minor components, and linear neural networks

Neural Networks
Original Contribution: Convergence analysis of local feature extraction algorithms

Neural Networks
Adaptive algorithms for first principal eigenvector computation

Neural Networks
Adaptive Principal component EXtraction (APEX) and applications

IEEE Transactions on Signal Processing
Global convergence of Oja's subspace algorithm for principal component extraction

IEEE Transactions on Neural Networks
Against the convergence of the minor component analysis neurons

IEEE Transactions on Neural Networks
Robust recursive least squares learning algorithm for principal component analysis

IEEE Transactions on Neural Networks
Algorithms for accelerated convergence of adaptive PCA

IEEE Transactions on Neural Networks
Local PCA algorithms

IEEE Transactions on Neural Networks
The MCA EXIN neuron for the minor component analysis

IEEE Transactions on Neural Networks
On the discrete-time dynamics of the basic Hebbian neural network node

IEEE Transactions on Neural Networks
Coupled principal component analysis

IEEE Transactions on Neural Networks
Convergence analysis of a deterministic discrete time system of Oja's PCA learning algorithm

IEEE Transactions on Neural Networks
Global analysis of Oja's flow for neural networks

IEEE Transactions on Neural Networks
Principal component extraction using recursive least squares learning

IEEE Transactions on Neural Networks
Dynamical system for computing the eigenvectors associated with the largest eigenvalue of a positive definite matrix

IEEE Transactions on Neural Networks
Energy function for the one-unit Oja algorithm

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.09

Visualization

Abstract

In most of existing principal components analysis (PCA) learning algorithms, the learning rates are required to approach zero as learning step increases. However, in many practical applications, due to computational round-off limitations and tracking requirements, constant learning rates must be used. This paper proposes a PCA learning algorithm with a constant learning rate. It will prove via DDT (Deterministic Discrete Time) method that this PCA learning algorithm is globally convergent. Simulations are carried out to illustrate the theory.