Hybrid ensembles and coincident-failure diversity

Proceedings of the International Joint Conference on Neural Networks

Volumn 4, Issue , 2001, Pages 2376-2381

  Wang, W ^a   Partridge, D ^a   Etherington, J ^a  

^a UNIVERSITY OF BRADFORD   (United Kingdom)

Author keywords

[No Author keywords available]

Indexed keywords

COMPUTER SOFTWARE; INFORMATION THEORY; LEARNING SYSTEMS; PROBABILITY; RANDOM PROCESSES;

COINCIDENT-FAILURE DIVERSITY; DECISION TREES;

FEEDFORWARD NEURAL NETWORKS;

EID: 0034871421     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Bagging predictors
2. A theoretical basis for the analysis of multiversion software subject to coincident errors
3. Experiments with a new boosting algorithm
4. Data mining of inputs: Analysis magnitude and functional measures
5. Neural network ensembles. IEEE trans.
6. Neural network ensembles, cross-validation and active learning
7. Multiple decision trees
8. Conceptual modelling of coincident failures in multiversion software
9. Engineering multiversion neural-net systems
10. Software diversity: Practical statistics for its measurement and exploitation
11. Induction of decision trees
12. Learning decision tree classifiers
13. Improved boosting algorithms using confidence-rated predictions
14. Establishing impacts of the inputs in a feedforward network
15. Decimated input ensembles for improved generalisation
16. Multiversion neural network systems
17. Ranking pattern recognition features for neural networks
18. Diversity between neural nets and decision trees for building multiple classifier systems
19. Assessing the impact of input features in a feedforward network
20. A comparative study of feature-salience ranking techniques