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

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.