Ensembling neural networks: Many could be better than all

Artificial Intelligence

Volumn 137, Issue 1-2, 2002, Pages 239-263

  Zhou, Zhi Hua ^a   Wu, Jianxin ^a   Tang, Wei ^a  

^a NANJING UNIVERSITY   (China)

Author keywords

Bagging; Bias variance decomposition; Boosting; Genetic algorithm; Machine learning; Neural network ensemble; Neural networks; Selective ensemble

Indexed keywords

ERROR ANALYSIS; GENETIC ALGORITHMS; PROBLEM SOLVING; REGRESSION ANALYSIS;

NEURAL NETWORK ENSEMBLE;

NEURAL NETWORKS;

EID: 0036567392     PISSN: 00043702     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0004-3702(02)00190-X     Document Type: Article

References (47)

1. An empirical comparison of voting classification algorithms: Bagging, Boosting, and variants
2. Bagging predictors
3. Human expert level performance on a scientific image analysis task by a system using combined artificial neural networks
4. Stability problems with artificial neural networks and the ensemble solution
5. Boosting using neural nets
6. Improving performance in neural networks using a boosting algorithm
7. Boosting a weak algorithm by majority
8. A decision-theoretic generalization of on-line learning and an application to boosting
9. Experiments with a new boosting algorithm
10. Neural networks and the bias/variance dilemma
11. Face recognition using hybrid classifier systems
12. A novel objective function for improved phoneme recognition using time-delay neural networks
13. Ensemble methods for handwritten digit recognition
14. Neural network ensembles
15. Pose invariant face recognition
16. Adaptively mixtures of local experts
17. Dynamically weighted ensemble neural networks for classification
18. Hierarchical mixtures of experts and the EM algorithm
19. Bias plus variance decomposition for zero-one loss functions
20. Error-correcting output coding corrects bias and variance
21. Neural network ensembles, cross validation, and active learning
22. Combining the predictions of multiple classifiers: Using competitive learning to initialize neural networks
23. A case study on bagging, boosting and basic ensembles of neural networks for OCR
24. Combining neural network regression estimates with regularized linear weights
25. Popular ensemble methods: An empirical study
26. Actively searching for an effective neural network ensemble
27. Generating accurate and diverse members of a neural network ensemble
28. When networks disagree: Ensemble method for neural networks
29. Bagging, Boosting, and C4.5
30. Boosting methodology for regression problems
31. Learning internal representations by error propagation
32. The strength of weak learnability
33. Classification of seismic signals by integrating ensembles of neural networks
34. Learning with ensembles: How over-fitting can be useful
35. Optimal linear combination of neural networks for improving classification performance
36. Stacked generalization
37. Making use of population information in evolutionary artificial neural networks
38. Lung cancer cell identification based on artificial neural network ensembles