A Theoretical and Experimental Account of N-Tuple Classifier Performance
Abstract
The n-tuple recognition method is briefly reviewed, summarizing the main theoretical results. Large-scale experiments carried out on Stat-Log project datasets confirm this method as a viable competitor to more popular methods due to its speed, simplicity, and accuracy on the majority of a wide variety of classification problems. A further investigation into the failure of the method on certain datasets finds the problem to be largely due to a mismatch between the scales which describe generalization and data sparseness.
Cite
Text
Rohwer and Morciniec. "A Theoretical and Experimental Account of N-Tuple Classifier Performance." Neural Computation, 1996. doi:10.1162/NECO.1996.8.3.629Markdown
[Rohwer and Morciniec. "A Theoretical and Experimental Account of N-Tuple Classifier Performance." Neural Computation, 1996.](https://mlanthology.org/neco/1996/rohwer1996neco-theoretical/) doi:10.1162/NECO.1996.8.3.629BibTeX
@article{rohwer1996neco-theoretical,
title = {{A Theoretical and Experimental Account of N-Tuple Classifier Performance}},
author = {Rohwer, Richard and Morciniec, Michal},
journal = {Neural Computation},
year = {1996},
pages = {629-642},
doi = {10.1162/NECO.1996.8.3.629},
volume = {8},
url = {https://mlanthology.org/neco/1996/rohwer1996neco-theoretical/}
}