The Theoretical and Experimental Status of the n-tuple Classifier

Abstract

A number of theoretical approaches related to the n-tuple classification system are reviewed including Kanerva's SDM, the n-tuple regression network, the Hamming distance framework and likelihood estimation. The limitations of these methods are pointed out and resemblances that exist between them are underlined. Large-scale experiments carried out on StatLog project datasets confirm the n-tuple 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 shows its inner workings and reveals two main problems: difficulties with highly skewed class priors and more importantly, a mismatch between the scales involved in generalization, the amount of training data available, and the volume of the region in which data is likely to exist. This highlights areas where improvements in the method are needed and further theoretical progress would be helpful.