Neural Network Ensembles |
Lars Kai Hansen, Peter Salamon
|
| Abstract | We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar networks. |
| Keywords | crossvalidation, fault tolerant computing,neural networks |
| Type | Journal paper [With referee] |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Year | 1990 Vol. 12 pp. 993-1001 |
| Electronic version(s) | [pdf] |
| BibTeX data | [bibtex] |
| IMM Group(s) | Intelligent Signal Processing |