– François Brucker (Centrale Marseille, LIF) : Latticial Approach for clustering problems

Carte non disponible

Date/heure
Date(s) - 20/06/2013
14 h 00 min - 15 h 00 min

Catégories Pas de Catégories


Latticial Approach for clustering problems By François Brucker, Centrale Marseille, LIF. We present a combinatorial model which generalizes phylogenetic trees. This model links together a graph model (strongly chordal graphs), a lattice model (crown-free lattices) and a clustering model (chordal quasi-ultrametrics). This structure allows to model networks and to associate attributes/labels to data. In classification, this kind of approximation yields a global visualization of the clusters and their relationships through dedicated 2-dimensional or 3-dimensional representations. It can be seen as a compromise between hierarchies (simple struc- ture; easy to interpret) and general lattices (rich interactions between elements; hard to interpret). We conclude be some open problems and possible links between this approach and machine learning methods like decision tree.

– François Brucker (Centrale Marseille, LIF) : Latticial Approach for clustering problems

Carte non disponible

Date/heure
Date(s) - 20/06/2013
14 h 00 min - 15 h 00 min

Catégories Pas de Catégories


Latticial Approach for clustering problems\nBy François Brucker, Centrale Marseille, LIF.\n\nWe present a combinatorial model which generalizes phylogenetic trees. This model links together a graph model (strongly chordal graphs), a lattice model (crown-free lattices) and a clustering model (chordal quasi-ultrametrics). This structure allows to model networks and to associate attributes/labels to data. In classification, this kind of approximation yields a global visualization of the clusters and their relationships through dedicated 2-dimensional or 3-dimensional representations. It can be seen as a compromise between hierarchies (simple struc- ture\ ; easy to interpret) and general lattices (rich interactions between elements\ ; hard to interpret).\n\nWe conclude be some open problems and possible links between this approach and machine learning methods like decision tree.[