Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate

DOI10.1016/j.tcs.2006.07.012zbMath1178.68439OpenAlexW2009787688MaRDI QIDQ857392

Jian Cheng Lv, Zhang Yi, Kok Kiong Tan

Publication date: 14 December 2006

Published in: Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.tcs.2006.07.012

zbMATH Keywords

global convergenceprincipal component analysisdeterministic discrete time systemOja's PCA learning algorithm

Mathematics Subject Classification ID

Nonnumerical algorithms (68W05) Learning and adaptive systems in artificial intelligence (68T05)

Related Items (6)

Convergence analysis of Oja's iteration for solving online PCA with nonzero-mean samples ⋮ Robust classifier using distance-based representation with square weights ⋮ Adaptive multiple minor directions extraction in parallel using a PCA neural network ⋮ Another neural network based approach for computing eigenvalues and eigenvectors of real skew-symmetric matrices ⋮ Online Principal Component Analysis in High Dimension: Which Algorithm to Choose? ⋮ Stochastic Gauss-Newton algorithms for online PCA

Cites Work

• Unnamed Item
• Adaptive algorithms for first principal eigenvector computation
• On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
• A simplified neuron model as a principal component analyzer
• Generalized neural networks for spectral analysis: dynamics and Liapunov functions
• Multilayer dynamic neural networks for non-linear system on-line identification

This page was built for publication: Global convergence of Oja's PCA learning algorithm with a non-zero-approaching adaptive learning rate