Neural network ensembles
- 1 January 1990
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 12 (10) , 993-1001
- https://doi.org/10.1109/34.58871
Abstract
Several means for improving the performance and training of neural networks for classification are proposed. Crossvalidation is used as a tool for optimizing network parameters and architecture. It is shown that the remaining residual generalization error can be reduced by invoking ensembles of similar networks.Keywords
This publication has 14 references indexed in Scilit:
- A statistical approach to learning and generalization in layered neural networksProceedings of the IEEE, 1990
- Protein secondary structure and homology by neural networks The α‐helices in rhodopsinFEBS Letters, 1988
- Predicting the secondary structure of globular proteins using neural network modelsJournal of Molecular Biology, 1988
- Generalization of back-propagation to recurrent neural networksPhysical Review Letters, 1987
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- A Learning Algorithm for Boltzmann Machines*Cognitive Science, 1985
- Optimization by Simulated AnnealingScience, 1983
- Broken ergodicityAdvances in Physics, 1982
- Molecular-dynamics study of a three-dimensional one-component model for distortive phase transitionsPhysical Review B, 1978
- Bibliography on estimation of misclassificationIEEE Transactions on Information Theory, 1974