A theory for learning based on rigid bodies dynamics

IEEE Transactions on Neural Networks

Volumn 13, Issue 3, 2002, Pages 521-531

  Fiori, Simone ^a  

^a UNIVERSITY OF PERUGIA   (Italy)

Author keywords

Matrix flows on Stiefel manifold; Orthonormal signal processing; Principal independent component analysis; Rational mechanics; Unsupervised neural learning

Indexed keywords

COMPUTER SIMULATION; LEARNING ALGORITHMS; NEURAL NETWORKS; PRINCIPAL COMPONENT ANALYSIS; SIGNAL PROCESSING;

RIGID BODIES DYNAMICS;

LEARNING SYSTEMS;

EID: 0036565608     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2002.1000121     Document Type: Article

References (45)

1. Global optimization and stochastic differential equations
2. Natural gradient works efficiently in learning
3. A new learning algorithm for blind signal separation
4. Rational kinematics
5. An information maximization approach to blind separation and blind deconvolution
6. Dynamical systems that sort lists, diagonalize matrices and solve linear programming problems
7. Equivariant adaptive source separation
8. Evolution, neural networks, games, and intelligence
9. Neural networks for blind separation with unknown number of sources
10. Independent component analysis, a new concept?
11. Improved contrast dedicated to blind separation in communications
12. The Helmholtz machine
13. Adaptive blind separation of independent sources: A deflation approach
14. An ordered-rotation Kuicnet algorithm for separating arbitrarily-distributed sources
15. The geometry of algorithms with orthogonality Constraints
16. Entropy optimization by the PFANN network: Application to independent component analysis
17. Mechanical' neural learning applied to blind source separation
18. Blind separation of circularly-distributed sources by neural extended Apex algorithm
19. Blind signal processing by the adaptive activation function neurons
20. A general class of ψ-APEX PCA neural algorithms
21. A theory for learning by weight flow on Stiefel-Grassman manifold
22. On blind separation of complex-valued sources by extended Hebbian learning
23. A constrained anti-Hebbian learning algorithm for total least-squares estimation with applications to adaptive FIR and IIR filtering
24. Independent component analysis by general nonlinear Hebbian-like rules
25. Neural approaches to independent component analysis and source separation
26. Optimization by simulated annealing
27. A survey of source separation
28. Neural-gas' network for vector quantization and its application to time-series prediction
29. Orthonormal wavelets with balanced uncertainty
30. Learning algorithm for ICA by geodesic flows on orthogonal group
31. Neural networks, principal components and subspaces
32. Information theoretic learning
33. Optimal unsupervised learning in a single-layered feed-forward network
34. Blind separation of convolved mixtures in the frequency domain
35. Maximum likelihood methods for DOA estimation
36. A cascade neural network for blind signal extraction without spurious equilibria
37. Mutual information in learning feature transformation
38. Statistical mechanics of mutual information maximization