Title :
Convergence analysis of a deterministic discrete time system of feng´s MCA learning algorithm
Author :
Peng, Dezhong ; Yi, Zhang
Author_Institution :
Coll. of Comput. Sci. & Eng., Univ. of Electron. Sci. & Technol. of China
Abstract :
The convergence of minor-component analysis (MCA) algorithms is an important issue with bearing on the use of these methods in practical applications. This correspondence studies the convergence of Feng´s MCA learning algorithm via a corresponding deterministic discrete-time (DDT) system. Some sufficient convergence conditions are obtained for Feng´s MCA learning algorithm with constant learning rate. Simulations are carried out to illustrate the theory
Keywords :
discrete time systems; matrix algebra; signal processing; convergence analysis; deterministic discrete time system; minor-component analysis algorithms; Algorithm design and analysis; Computational complexity; Convergence; Discrete cosine transforms; Discrete time systems; Least squares approximation; Signal processing algorithms; Stochastic processes; Stochastic systems; Surface fitting; Deterministic discrete-time (DDT) system; eigenvalue; eigenvector; minor-component analysis (MCA); neural network;
Journal_Title :
Signal Processing, IEEE Transactions on
DOI :
10.1109/TSP.2006.877662
