Convergence analysis of local feature extraction algorithms

Neural Networks

Volumn 5, Issue 2, 1992, Pages 229-240

  Hornik, K ^a   Kuan, C M ^b  

^a VIENNA UNIVERSITY OF TECHNOLOGY   (Austria)

^b UNIVERSITY OF ILLINOIS AT URBANA CHAMPAIGN   (United States)

Author keywords

Feature extraction algorithm; Hebbian learning; Principal component analysis

Indexed keywords

COMPUTER PROGRAMMING - ALGORITHMS; NEURAL NETWORKS; PATTERN RECOGNITION;

CONVERGENCE ANALYSIS; FEATURE EXTRACTION; LEARNING ALGORITHMS; PRINCIPAL COMPONENTS ANALYSIS;

LEARNING SYSTEMS;

EID: 0026727495     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(05)80022-X     Document Type: Article

References (24)

1. An empirical process central limit theorem for dependent non-identically distributed random variables
2. Linear learning: Landscapes and algorithms
3. Back-propagation and unsupervised learning in linear networks
4. Adaptation and decorrelation in the cortex
5. Auto-association by multilayer perceptrons and singular value decomposition
6. Adaptive network for optimal linear feature extraction
7. Hebbian learning of principal components
8. Convergence of learning algorithms with constant learning rates
9. A neural network learning algorithm for adaptive principal component extraction (APEX)
10. Self-organization in a perceptual network
11. Analysis of recursive stochastic algorithms
12. A maximal inequality and dependent strong laws
13. A simplified neuron model as a principal component analyzer
14. Neural networks principal components and subspaces
15. On stochastic approximation of the eigenvectors and the eigenvalues of the expectation of a random matrix
16. A self-organizing network for principal component analysis
17. Optimal unsupervised learning in a single-layer linear feedforward neural network
18. Feature discovery through error-correction learning