Modified Hebbian learning for curve and surface fitting

Neural Networks

Volumn 5, Issue 3, 1992, Pages 441-457

  Xu, Lei ^a,b   Oja, Erkki ^c   Suen, Ching Y ^b  

^a HARVARD UNIVERSITY   (United States)

^b Gina Cody School of Engineering and Computer Science   (United States)

^c LAPPEENRANTA UNIVERSITY OF TECHNOLOGY   (Finland)

Author keywords

Curve and surface fitting; Hebbian learning; Minor components; Principal component analysis; Stochastic approximation; Total least square method

Indexed keywords

LEARNING SYSTEMS; MATHEMATICAL TECHNIQUES - LEAST SQUARES APPROXIMATIONS;

CURVE AND SURFACE FITTING; HEBBIAN LEARNING; LEARNING RULE; PRINCIPAL COMPONENT ANALYSIS; STOCHASTIC APPROXIMATION;

NEURAL NETWORKS;

EID: 0026745682     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/0893-6080(92)90006-5     Document Type: Article

References (24)

1. Neural networks and principal component analysis: Learning from examples without local minima
2. Back-propagation and unsupervised learning in linear networks
3. Principal component analysis by gradient descent on a constrained linear Hebbian cell
4. Adaptive network for optimal linear feature extraction
5. Learning, invariance, and generalization in high order neural networks
6. On the recursive estimation of the eigenvectors of correlation type matrices
7. Constrained principal component analysis via an orthogonal learning network
8. A neural networks learning algorithm for adaptive principal component extraction (APEX)
9. From basic network principles to neural architecture: Emergence of spatial opponent cells
10. From basic network principles to neural architecture: Emergence of orientation selective cells
11. From basic network principles to neural architecture: Emergence of orientation columns
12. Analysis of recursive stochastic algorithms
13. A simplified neuron model as a principal component analyzer
14. Neural networks principal components and subspaces
15. On stochastic approximation of eigenvectors and eigenvalues of the expectation of a random matrix
16. Learning in non-linear constrained Hebbian networks
17. On lines and planes of closest fit to points in space
18. A stochastic approximation method
19. A self-organizing network for principal-component analysis
20. Development of feature detectors by self-organization
21. Optimal unsupervised learning in a single-layer linear feed forward neural network