Selecting inputs for modeling using normalized higher order statistics and independent component analysis

IEEE Transactions on Neural Networks

Volumn 12, Issue 3, 2001, Pages 612-617

  Back, Andrew D ^a   Trappenberg, Thomas P ^a,b  

^a RIKEN BRAIN SCIENCE INSTITUTE   (Japan)

^b UNIVERSITY OF OXFORD   (United Kingdom)

Author keywords

Higher order statistics; Independent component analysis; Input variable selection

Indexed keywords

ALGORITHMS; COMPUTATIONAL COMPLEXITY; COMPUTER SIMULATION; INDEPENDENT COMPONENT ANALYSIS; LEARNING SYSTEMS; MATRIX ALGEBRA; PROBABILITY DENSITY FUNCTION; STATISTICAL TESTS; STATISTICS;

HIGH ORDER STATISTICS; INPUT VARIABLE SELECTION; MODEL FREE METHODS;

NEURAL NETWORKS;

EID: 0035329583     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.925564     Document Type: Article

References (16)

1. Selecting input variables using mutual information and nonparamteric density estimation
2. Nonlinear dimensionality reduction
3. Optimal brain damage
4. Second-order derivatives for network pruning: Optimal brain surgeon
5. A simple procedure for pruning backpropagation trained neural networks
6. Pruning from adaptive regularization
7. Pruning with replacement on limited resource allocating networks by f-projections
8. Pruning recurrent neural networks for improved generalization performance
9. An iterative pruning algorithm for feedforward neural networks
10. A comparison of pruning techniques to enhance network generalization performance
11. Pruning algorithms - A survey
12. Blind separation of sources, part I: An adaptive algorithm based on neuromimetic architecture
13. Blind signal processing: Neural-network approaches
14. Fast pruning using principal components
15. Dimension reduction by local principal component analysis