Hybrid independent component analysis by adaptive LUT activation function neurons

Neural Networks

Volumn 15, Issue 1, 2002, Pages 85-94

  Fiori, Simone ^a  

^a UNIVERSITY OF PERUGIA   (Italy)

Author keywords

Adaptive activation function neurons; Independent component analysis; Kullback Leibler divergence; Look up table neurons; Minimal mutual information principle; Natural gradient

Indexed keywords

ADAPTIVE SYSTEMS; PROBABILITY DENSITY FUNCTION; SIGNAL PROCESSING;

ADAPTIVE ACTIVATION FUNCTION NEURONS;

NEURAL NETWORKS;

ARTICLE; CELL ACTIVATION; CELL DENSITY; CELL FUNCTION; NERVE CELL; PRIORITY JOURNAL; PRODUCTIVITY; SIGNAL PROCESSING;

EID: 0036120077     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(01)00105-8     Document Type: Article

References (48)

1. Natural gradient works efficiently in learning
2. An information maximisation approach to blind separation and blind deconvolution
3. Maximum likelihood source separation by the expectation-maximization technique: Deterministic and stochastic implementation
4. Blind signal separation: Statistical principles
5. High-order contrasts for independent component analysis
6. Equivarient adaptive source separation
7. A class of local interpolating splines
8. A feedforward neural network with function shape autotuning
9. Conventional modeling of the multi-layer perceptron using polynomial basis functions
10. Independent component analysis, a new concept?
11. Improved contrast dedicated to blind separation in communications
12. Image compression using principal component neural networks
13. Storage capacity of non-monotonic neurons
14. Maximum likelihood for incomplete data via the EM algorithm
15. Entropy optimization by the PFANN network: Application to independent component analysis
16. Blind signal processing by the adaptive activation function neurons
17. Blind separation of circularly distributed source signals by the neural extended APEX algorithm
18. A theory for learning by weight flow on Stiefel-Grassman manifold
19. Notes on cost functions and estimators for 'Bussgang' adaptive blind equalization
20. Probability density estimation using adaptive activation function neurons
21. Weighted least-squares blind deconvolution of non-minimum phase systems
22. A general class of ψ-APEX PCA neural algorithms
23. Extraction of independent signal sources using a deflationary exploratory projection pursuit network with lateral inhibition
24. Gaussian mixture and kernel based approach to blind source separation using neural networks
25. The study of neural network control system
26. A fast fixed-point algorithm for independent component analysis
27. Data pre-distortion techniques using intersymbol interpolation
28. A class of neural networks for independent component analysis
29. Bayesian source separation and localization
30. Independent component analysis using an extended informax algorithm for mixed sub-Gaussian and super-Gaussian sources
31. Adaptive polynomial filtering
32. Learning algorithm for ICA by geodesic flows on orthogonal group
33. The nonlinear PCA learning rule in independent component analysis
34. Averaging, maximum penalized likelihood and Bayesian estimation for improving Gaussian mixture probability density estimates
35. Unmixing hyperspectral data
36. Maximum likelihood blind source separation; a context-sensitive generalization of ICA
37. Separation of a mixture of independent sources through a maximum likelihood approach
38. Neural networks with digital LUT activation function
39. Neural net approach for blind separation of sources based on geometric properties
40. Independent component analysis: Source assessment and separation, a Bayesian approach
41. Entropy optimization - Application to source separation
42. Networks with trainable amplitude of activation
43. A cascade neural network for blind signal extraction without spurious equilibria
44. Learning and approximation capabilities of adaptive spline activation function neural networks
45. Learned parametric mixture based ICA algorithm
46. Neural network controller using autotuning method for non-linear functions
47. Adaptive online learning algorithms for blind separation: Maximum entropy and minimum mutual information