The dynamics of on-line principal component analysis

DOI10.1088/0305-4470/31/5/002MaRDI QIDQ4486368zbMATH OpenOpenAlexWikidataFDO

Authors E. Schlösser, Michael Biehl

Publication date 26 June 2000

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/a8061bf0a65b7d8b21eeefe08d0359a8f4b3ee62

zbMATH Keywords

coupled ordinary differential equationslearning dynamicson-line algorithmprincipal component analysisSanger's rulethermodynamic limit

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Recommendations

• Optimization of on-line principal component analysis
• Online principal components analysis
• scientific article; zbMATH DE number 1569111
• 10.1162/jmlr.2003.4.7-8.1393
• Near-optimal stochastic approximation for online principal component estimation
• Online algorithm of coupled principal (minor) component analysis
• On the optimality of the Oja's algorithm for online PCA
• A Fixed-Point Online Kernel Principal Component Extraction Algorithm

Cited in

(12)

• On principal subspace analysis
• Interlocking of learning and orthonormalization in RRLSA.
• Perturbation scheme for online learning of features: Incremental principal component analysis
• Stochastic trapping in a solvable model of on-line independent component analysis
• A Hebb-type learning equation on the quantum information space - a clue to a fast principal component analyzer
• 10.1162/jmlr.2003.4.7-8.1393
• scientific article; zbMATH DE number 1569111 (Why is no real title available?)
• Optimization of on-line principal component analysis
• The scaling limit of high-dimensional online independent component analysis
• On the optimality of the Oja's algorithm for online PCA
• Convergence proof of matrix dynamics for online linear discriminant analysis
• The dynamics of representation learning in shallow, non-linear autoencoders

This page was built for publication: The dynamics of on-line principal component analysis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4486368)