Similarity and dissimilarity measures

Clustering involves identifying groupings of data. This is possible thanks to the measure of the proximity between the elements. The term proximity is used to refer to either similarity or dissimilarity. So, a group of data can be defined once you have chosen how to define the concept of similarity or dissimilarity. In many approaches, this proximity is conceived in terms of distance in a multidimensional space. The quality of the analysis obtained from clustering algorithms depends a lot on the choice of metric, hence, on how the distance is calculated. Clustering algorithms group elements based on their reciprocal distance, so belonging to a set depends on how close the element under consideration is ...

Get MATLAB for Machine Learning now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.