Hierarchical clustering based on the information bottleneck method using a control process

Full Text
Hierarchical-clustering.pdf embargoed access
Request a copy
When filling the form you are requesting a copy of the article, that is deposited in the institutional repository (DUGiDocs), at the autor or main autor of the article. It will be the same author who decides to give a copy of the document to the person who requests it, if it considers it appropriate. In any case, the UdG Library doesn’t take part in this process because it is not authorized to provide restricted articles.
Clustering techniques aim organizing data into groups whose members are similar. A key element of these techniques is the definition of a similarity measure. The information bottleneck method provides us a full solution of the clustering problem with no need to define a similarity measure, since a variable is clustered depending on a control variable by maximizing the mutual information between them. In this paper, we propose a hierarchical clustering algorithm based on the information bottleneck method such that, instead of using a control variable, the different possible values of a Markov process are clustered by maximally preserving the mutual information between two consecutive states of the Markov process. These two states can be seen as the input and the output of an information channel that is used as a control process, similarly to how the variable is used as a control variable in the original information bottleneck algorithm. We present both agglomerative and divisive versions of our hierarchical clustering approach and two different applications. The first one, to quantize an image by grouping intensity bins of the image histograms, is tested on synthetic, photographic and medical images and compared with hand-labelled images, hierarchical clustering using Euclidean distance and non-negative matrix factorization methods. The second one, to cluster brain regions by grouping them depending on their connectivity, is tested on medical data. In all the applications, the obtained results demonstrate the efficacy of the method in getting clusters with high mutual information. ​
​Tots els drets reservats