Please use this identifier to cite or link to this item:
Title: Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate
Authors: Cheng Lv, J.
Yi, Z.
Tan, K.K. 
Keywords: Deterministic discrete time system
Global convergence
Oja's PCA learning algorithm
Principal component analysis (PCA)
Issue Date: 1-Dec-2006
Citation: Cheng Lv, J., Yi, Z., Tan, K.K. (2006-12-01). Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate. Theoretical Computer Science 367 (3) : 286-307. ScholarBank@NUS Repository.
Abstract: A non-zero-approaching adaptive learning rate is proposed to guarantee the global convergence of Oja's principal component analysis (PCA) learning algorithm. Most of the existing adaptive learning rates for Oja's PCA learning algorithm are required to approach zero as the learning step increases. However, this is not practical in many applications due to the computational round-off limitations and tracking requirements. The proposed adaptive learning rate overcomes this shortcoming. The learning rate converges to a positive constant, thus it increases the evolution rate as the learning step increases. This is different from learning rates which approach zero which slow the convergence considerably and increasingly with time. Rigorous mathematical proofs for global convergence of Oja's algorithm with the proposed learning rate are given in detail via studying the convergence of an equivalent deterministic discrete time (DDT) system. Extensive simulations are carried out to illustrate and verify the theory derived. Simulation results show that this adaptive learning rate is more suitable for Oja's PCA algorithm to be used in an online learning situation. © 2006 Elsevier B.V. All rights reserved.
Source Title: Theoretical Computer Science
ISSN: 03043975
DOI: 10.1016/j.tcs.2006.07.012
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Jul 3, 2020


checked on Jun 25, 2020

Page view(s)

checked on Jun 29, 2020

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.