Least mean square error reconstruction principle for self-organizing neural-nets

Neural Networks

Volumn 6, Issue 5, 1993, Pages 627-648

  Xu, Lei ^a  

^a PEKING UNIVERSITY   (China)

Author keywords

Convergence analysis; Least MSE reconstruction; PCA nets; Self organization; Symmetry breaking

Indexed keywords

CONVERGENCE OF NUMERICAL METHODS; ERROR ANALYSIS; LEAST SQUARES APPROXIMATIONS; MATHEMATICAL MODELS; NUMERICAL ANALYSIS; STATISTICAL METHODS;

CONVERGENCE ANALYSIS; LEAST MEAN SQUARE ERROR RECONSTRUCTION (LMSER); PRINCIPAL COMPONENT ANALYSIS (PCA); SELF ORGANIZATION; SYMMETRY BREAKING;

NEURAL NETWORKS;

EID: 0027206958     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(05)80107-8     Document Type: Article

References (58)

1. Competitive learning algorithms for vector quantization
2. Neural networks and principal component analysis: Learning from examples without local minima
3. Back-propagation and unsupervised learning in linear networks
4. Unsupervised learning
5. Learning receptive fields
6. Self-organizing neural network that discover surfaces in random-dot stereogram
7. Theory for the development of neuron selectivity: Orientation specificity and binocular interaction in visual cortex
8. Dynamical systems that sort lists, diagonalize matrices, and solve linear programming problems
9. A massively parallel architecture for a self-organizing neural pattern recognition machine
10. ART2 Self-organization of stable category recognition codes fo analog input patterns
11. The ART of adaptive pattern recognition by a self-organizing neural network
12. ART3: Hierarchical searching using chemical transmitters in self-organizing pattern recognition architectures
13. Nonlinear prediction of chaotic time series
14. Principal component analysis by gradient descent on a constrained linear Hebbian cell
15. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks
16. Adding a conscience to competitive learning
17. Adaptive network for optimal linear feature extraction
18. Cognitron: A self-organizing multilayered neural network
19. Neocognitron: A self-organizing neural model for a mechanism of pattern recognition unaffected by shift in position
20. On learning and energy entropy dependence in recurrent and nonrecurrent signed networks
21. Neural expectation: Cerebellar and retinal analogs of cells fired by learnable or unlearned pattern classes
22. Contour enhancement, short term memory, and constancies in reverberating neural networks
23. Adaptive pattern classification and universal recording: I. Parallel development and coding of neural feature detectors
24. Adaptive pattern classification and universal recording: II. Feedback, expectation, olfaction, illusions
25. Competitive learning: From interactive activation to adaptive resonance
26. Counterpropagation networks
27. Receptive fields, binocular interaction, and functional architecture in the cat's visual cortex
28. Neural Networks and physical systems with emergent collective computational abilities
29. Neurons with graded responses have collective computational abilities like those of two-state neurons
30. Convergence analysis of local feature extraction algorithms
31. Self-organization by delta rule
32. Adaptive mixtures of local experts
33. Spontaneous symmetry-breaking energy functions and the emergence of orientation selective cortical cells
34. Self-organized formation of topologically correct feature maps
35. Hebbian learning of principal components
36. Constrained principal component analysis via an orthogonal learning network
37. From basic network principles to neural architecture
38. From basic network principles to neural architecture
39. From basic network principles to neural architecture
40. Self-organization in a perceptual network
41. Self-organization of orientation sensitive cells in the striate cortex
42. Fast learning in networks of locally-tuned processing units
43. From competitive learning to adaptive mixtures of experts
44. A simplified neuron model as a principal component analyzer
45. Neural networks principal components and subspaces
46. Learning in nonlinear constrained Hebbian networks
47. Regularization algorithms for learning that are equivalent to multilayer networks
48. A self-organizing network for principal-component analysis
49. Development of feature detectors by self-organization
50. Feature discovery by competitive learning
51. Optimal unsupervised learning in a single-layer linear feed forward neural network
52. Least MSE reconstruction for self-organization: (I) Multi-layer neural-nets and (II) further theoretical and experimental studies on one layer nets
53. Modified Habbian learning for curve and surface fitting
54. Quadrature and the development of orientation selective cortical cells by Hebb rules