Novel neural network feature selection procedure by generalization maximization with application to automatic robot guidance

International Journal of Smart Engineering System Design

Volumn 4, Issue 2, 2002, Pages 91-106

  Fiori, Simone ^a   Grimani, Francesco ^a   Burrascano, Pietro ^a  

^a UNIVERSITY OF PERUGIA   (Italy)

Author keywords

Automatic robot guidance; Feature selection; Generalization maximization; Network complexity reduction by pruning; Neural networks; Relevance determination

Indexed keywords

ALGORITHMS; CAMERAS; DIGITAL DEVICES; ROBOT APPLICATIONS;

AUTOMATIC ROBOT GUIDANCE;

NEURAL NETWORKS;

EID: 0036529665     PISSN: 10255818     EISSN: None     Source Type: Journal    
DOI: 10.1080/10255810212402     Document Type: Article

References (48)

1. Artificial neural networks for image analysis and computer vision
2. A general class of ΨAPEX PCA neural algorithms
3. A probabilistic model for appearance-based robot localization
4. Blind signal processing by the adaptive activation function neurons
5. Blind separation of circularly-distributed sources by neural extended APEX algorithm
6. Hybrid independent component analysis by adaptive LUT activation function neurons
7. Using mutual information for selecting features is supervised neural net learning
8. Mutual information feature extractors for neural classifiers
9. A practical bayesian framework for backprop networks
10. A pruning technique maximizing generalization
11. A simple procedure for pruning back-propagation trained neural networks
12. Neural network feature selection
13. A simple neural network pruning algorithm with application to filter synthesis
14. Improving generalization of neural networks through pruning
15. A comment on noise injection into inputs in back-propagation learning
16. Noise injection for inputs relevance determination
17. What size network is good for generalization of a specific task of interest?
18. Irrelevant features and the subset selection problem
19. Selection of relevant features in machine learning
20. Using an MDL-based cost function with neural networks
21. Feature selection via mathematical programming
22. Feature selection via concave miniaturization and support vector machines
23. Propagation algorithm for variational bayesian learning
24. Feature selection by a genetic algorithm. Application to seed discrimination by artificial vision
25. Practical feature subset selection for machine learning
26. Some issues on scalable feature selection
27. Bayesian non-linear modelling for the energy prediction competition
28. An optimal criterion of NN structure selection for financial forecasting
29. A review of bayesian neural networks with an application to near infrared spectroscopy
30. Training data representation in a neural based robot position estimation system
31. Recursive 3-D road and relative ego-state recognition
32. Mobile robot navigation using neural networks and nonmetrical environmental models
33. Plan guided reaction
34. VITS - A vision system for autonomous land vehicle navigation
35. Progress in robot road following
36. Neural network feature selection applied to robot motion control
37. Bayesian interpolation
38. Coefficient accuracy and digital filter response
39. Generalization ability of perceptrons with continuous outputs
40. The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems
41. Skeletonization: A technique for trimming the fat from a network via relevance asessment
42. A statistical approach to learning and generalization in layered neural networks
43. Statistical theory of learning curves under entropic loss criterion
44. Training with noise is equivalent to Tikhonov regularization