Generalizations of principal component analysis, optimization problems, and neural networks

Neural Networks

Volumn 8, Issue 4, 1995, Pages 549-562

  Karhunen, Juha ^a   Joutsensalo, Jyrki ^a  

^a AALTO UNIVERSITY   (Finland)

Author keywords

Generalized Hebbian algorithm; Neural network; Nonlinearity; Oja's rule; Optimization; Principal components; Robust statistics; Unsupervised learning

Indexed keywords

CONSTRAINT THEORY; DATA STRUCTURES; EIGENVALUES AND EIGENFUNCTIONS; HIERARCHICAL SYSTEMS; INFORMATION THEORY; LEARNING ALGORITHMS; LEARNING SYSTEMS; MATHEMATICAL TRANSFORMATIONS; OPTIMIZATION; STATISTICAL METHODS; STATISTICS; VECTORS;

DATA VECTOR; GENERALIZED HEBBIAN ALGORITHM; MEAN SQUARE ERROR MINIMIZATION; PRINCIPAL COMPONENT ANALYSIS; SECOND ORDER STATISTICS; VARIANCE MAXIMIZATION;

NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL INTELLIGENCE; COMPUTER MODEL; CONTROLLED STUDY; LEARNING; PRIORITY JOURNAL;

EID: 0029061996     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(94)00098-7     Document Type: Article

References (49)

1. Neural networks for principal component analysis: Learning from examples without local minima
2. Relations between variants of non-linear principal components analysis
3. Auto-association by multilayer perceptrons and singular value decomposition
4. Blind separation of sources: A nonlinear neural algorithm
5. Robust estimation of principal components by using neural network learning algorithms
6. Independent component analysis—a new concept?
7. Nonlinear multivariate analysis
8. Principal Curves
9. Nonlinear multilayer principal component type subspace learning algorithms
10. Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture
11. A fast non-linear dimension reduction
12. Stability of Oja's PCA subspace rule
13. Learning of sinusoidal frequencies by nonlinear constrained Hebbian algorithms
14. Learning of robust principal component subspace
15. Nonlinear generalizations of principal component learning algorithms
16. Representation and separation of signals using nonlinear PCA type learning
17. Local synaptic learning rules suffice to maximize mutual information in a linear network
18. Deriving receptive fields using an optimal encoding criterion
19. Signal processing with higherorder spectra
20. Principal components, minor components, and linear neural networks
21. Nonlinear PCA: Algorithms and applications
22. Learning in nonlinear constrained Hebbian networks
23. Principal component analysis by homogeneous neural networks, part II: Analysis and extensions of the learning algorithms
24. Unsupervised parallel feature extraction from first principles
25. Hebbian learning and self-association in nonlinear neural networks
26. Hebbian learning in linear neural networks: A review
27. Anti-Hebbian learning in topologically constrained linear networks: A tutorial
28. Efficient information transfer and antiHebbian neural networks
29. A Hebbian/anti-Hebbian network which optimizes information capacity by orthonormalizing the principal subspace
30. An optimality principle for unsupervised learning
31. Optimal unsupervised learning in a singlelayer linear feedforward network
32. Nonlinear Hebbian rule A statistical interpretation
33. Information theory and neural networks
34. Least mean square error reconstruction principle for self-organizing neural-nets
35. Theories for unsupervised learning: PCA and its nonlinear extensions
36. Self-organizing rules for robust principal component analysis