Growing selforganizing trees for autonomous hierarchical clustering Presenter

  • Slides: 18
Download presentation
Growing self-organizing trees for autonomous hierarchical clustering Presenter: MIN-CHIEH HSIU Authors: NHAT-QUANG DOAN∗, HANANE

Growing self-organizing trees for autonomous hierarchical clustering Presenter: MIN-CHIEH HSIU Authors: NHAT-QUANG DOAN∗, HANANE AZZAG, MUSTAPHA LEBBAH 2013 NN Intelligent Database Systems Lab

Outlines n Motivation n Objectives n Methodology n Experimental Result n Conclusions n Comments

Outlines n Motivation n Objectives n Methodology n Experimental Result n Conclusions n Comments Intelligent Database Systems Lab

Motivation • Discovering the inherent structure and its uses in large datasets has become

Motivation • Discovering the inherent structure and its uses in large datasets has become a major challenge for data mining applications. Intelligent Database Systems Lab

Objectives • This authors aim to build an autonomous hierarchical clustering system using the

Objectives • This authors aim to build an autonomous hierarchical clustering system using the self-organization concept that runs autonomously without using parameters. • GSo. T: Growing Self-organizing Trees. Intelligent Database Systems Lab

GSo. T algorithm • X = {xi; i = 1, . . . ,

GSo. T algorithm • X = {xi; i = 1, . . . , N} a set of N observations. • List denotes the set that contains all observations. • Each treesi is associated with a weight vector, denoted by wsi Intelligent Database Systems Lab

GSo. T algorithm function status (xi) • initial: the default status before training. •

GSo. T algorithm function status (xi) • initial: the default status before training. • connected: node xi is currently connected to another node. • disconnected: node xi was connected at least once but gets disconnected. Intelligent Database Systems Lab

GSo. T algorithm 1 Intelligent Database Systems Lab

GSo. T algorithm 1 Intelligent Database Systems Lab

GSo. T algorithm 2 Intelligent Database Systems Lab

GSo. T algorithm 2 Intelligent Database Systems Lab

GSo. T algorithm 3 Intelligent Database Systems Lab

GSo. T algorithm 3 Intelligent Database Systems Lab

GSo. T algorithm 4 Intelligent Database Systems Lab

GSo. T algorithm 4 Intelligent Database Systems Lab

Experiment-performance Intelligent Database Systems Lab

Experiment-performance Intelligent Database Systems Lab

Experiment-Visual validation • Its main advantage is that it provides simultaneous topological and hierarchical

Experiment-Visual validation • Its main advantage is that it provides simultaneous topological and hierarchical organization. Intelligent Database Systems Lab

vote Intelligent Database Systems Lab

vote Intelligent Database Systems Lab

Intelligent Database Systems Lab

Intelligent Database Systems Lab

Intelligent Database Systems Lab

Intelligent Database Systems Lab

Intelligent Database Systems Lab

Intelligent Database Systems Lab

Conclusions • This paper presents a new approach that allows for simultaneous clustering and

Conclusions • This paper presents a new approach that allows for simultaneous clustering and visualization. • The tree structure allows the user to understand analyze large amounts of data in an explorative manner. Intelligent Database Systems Lab

Comments • This paper presents GSo. T improved interactive visualization and clustered efficiency for

Comments • This paper presents GSo. T improved interactive visualization and clustered efficiency for data. • Application. Data visualization Clustering Intelligent Database Systems Lab

Clustering kMeans hierarchical clustering SelfOrganizing Maps Outline kmeansClustering kMeans hierarchical clustering SelfOrganizing Maps Outline kmeans
Clustering kMeans hierarchical clustering SelfOrganizing Maps Outline kmeansClustering kMeans hierarchical clustering SelfOrganizing Maps Outline kmeans
Clustering kMeans hierarchical clustering SelfOrganizing Maps Outline kmeansClustering kMeans hierarchical clustering SelfOrganizing Maps Outline kmeans
Clustering kMeans hierarchical clustering SelfOrganizing Maps Outline kmeansClustering kMeans hierarchical clustering SelfOrganizing Maps Outline kmeans
Hierarchical Clustering Hierarchical Clustering Produces a set ofHierarchical Clustering Hierarchical Clustering Produces a set of
Hierarchical Clustering Hierarchical Clustering Produces a set ofHierarchical Clustering Hierarchical Clustering Produces a set of
HIERARCHICAL CLUSTERING Hierarchical Clustering adalah metode analisis kelompokHIERARCHICAL CLUSTERING Hierarchical Clustering adalah metode analisis kelompok
Hierarchical Clustering Hierarchical Clustering Produces a set ofHierarchical Clustering Hierarchical Clustering Produces a set of
Hierarchical Clustering Hierarchical Clustering Produces a set ofHierarchical Clustering Hierarchical Clustering Produces a set of
HIERARCHICAL CLUSTERING HIERARCHICAL CLUSTERING Strategi pengelompokkannya umumnya adaHIERARCHICAL CLUSTERING HIERARCHICAL CLUSTERING Strategi pengelompokkannya umumnya ada
FLAT CLUSTERING HIERARCHICAL CLUSTERING What is clustering GroupingFLAT CLUSTERING HIERARCHICAL CLUSTERING What is clustering Grouping
Clustering Outline Introduction Kmeans clustering Hierarchical clustering COBWEBClustering Outline Introduction Kmeans clustering Hierarchical clustering COBWEB
Tournament Trees Winner trees Loser Trees Winner TreesTournament Trees Winner trees Loser Trees Winner Trees
Tournament Trees Winner trees Loser Trees Winner TreesTournament Trees Winner trees Loser Trees Winner Trees
Selection Trees Winner trees Loser Trees Winner TreesSelection Trees Winner trees Loser Trees Winner Trees
Trees trees binary trees traversals of trees templateTrees trees binary trees traversals of trees template
SelfOrganization SelfOrganizing Lists 1 Selforganizing lists modify theSelfOrganization SelfOrganizing Lists 1 Selforganizing lists modify the