x′) + d(x′, z) ≥ d(x, z), d(x, x′) = d(x′, x) • The selection of the distance measure is a user defined parameter and leads to a wide selection of viable options • Results may vary significantly depending on the distance measure that is selected • As always, its up to the designer to select a measure that works • Can you think of some measures of distance? • Manhattan, Euclidean, Spearman, Hellinger, Chord, Bhattacharyya, Mahalanobis, Hamming, Jaccard, . . . • Is Kullback–Leibler divergence considered a distance as defined above? 25 / 48