Principal components, minor components, and linear neural networks

Neural Networks

Volumn 5, Issue 6, 1992, Pages 927-935

  Oja, Erkki ^a  

^a LAPPEENRANTA UNIVERSITY OF TECHNOLOGY   (Finland)

Author keywords

Eigenvector; Generalized Hebbian Algorithm; Minor components; Neural networks; Stochastic gradient ascent; Subspace network

Indexed keywords

ALGORITHMS; DATA COMPRESSION; EIGENVALUES AND EIGENFUNCTIONS; LEARNING SYSTEMS; VECTORS;

EIGENVECTOR; GENERALIZED HEBBIAN ALGORITHM; MINOR COMPONENTS; PRINCIPAL COMPONENT ANALYSIS (PCA); STOCHASTIC GRADIENT ASCENT; SUBSPACE NETWORK;

NEURAL NETWORKS;

EID: 0026954958     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(05)80089-9     Document Type: Article

References (34)

1. Neural networks and principal components analysis: Learning from examples without local minima
2. Back-propagation and unsupervised learning in linear networks
3. Unsupervised learning procedures for neural networks
4. Auto-association by multilayer perceptrons and singular value decomposition
5. Principal component analysis by gradient descent on a constrained linear Hebbian cell
6. Tracking a few extreme singular values and vectors in signal processing
7. Image compression by back-propagation: A demonstration of extensional programming
8. Adaptive network for optimal linear feature extraction
9. Comparison of the cosine and Fourier Transforms of Markov-1 signals
10. Convergence analysis of local feature extraction algorithms
11. Recursive estimation of eigenvectors of correlation type matrices for signal processing applications
12. Tracking of sinusoidal frequencies by neural network learning algorithms
13. Hebbian learning of principal components
14. A neural network learning algorithm for adaptive principal component extraction (APEX)
15. MPEG: A video compression standard for multimedia applications
16. Self-organization in a perceptual network
17. Projection Filter, Wiener Filter, and Karhunen-Loeve Subspaces in digital image restoration
18. A simplified neuron model as a principal components analyzer
19. Neural networks principal components and subspaces
20. Data compression, feature extraction, and autoassociation in feed-forward neural networks
21. On stochastic approximation of the eigenvectors and eigenvalues of the expectation of a random matrix
22. Learning in non-linear constrained Hebbian networks
23. Principal Component Analysis by homogeneous neural networks, Part I: The Weighted Subspace criterion
24. Principal Component Analysis by homogeneous neural networks, Part II: Analysis and extensions of the learning algorithms
25. A self-organizing network for principal components analysis
26. Optimal unsupervised learning in a single-layer linear feedforward network
27. A fast neural algorithm for principal component analysis and singular value decomposition
28. An adaptive spectral analysis technique for unbiased frequency estimation in the presence of white noise
29. Feature discovery through error-correcting learning
30. Neural nets for dual subspace pattern recognition method
31. Modified Hebbian learning for curve and surface fitting