Zero-error dissimilarity based classifiers

Abstract

We consider general non-Euclidean distance measures between real world objects that need to be classified. It is assumed that objects are represented by distances to other objects only. Conditions for zero-error dissimilarity based classifiers are derived. Additional conditions are given under which the zero-error decision boundary is a continues function of the distances to a finite set of training samples. These conditions affect the objects as well as the distance measure used. It is argued that they can be met in practice.

arXiv comment5 pages. Paper originally written in 2003. Although it may proof an obvious fact, it is significant for understanding the essential conditions it is based on