Lien ebook : http://ezproxy.univ-catholille.fr/login?url=https://www.vleb...

eISBN : 9781118649497

Sommaire : Introduction

Types and representation of data
Simultaneous analysis
Notation
Different approaches
Model-based co-clustering

1. Cluster Analysis
Introduction
Miscellaneous clustering methods
Model-based clustering and the mixture model
EM algorithm
Clustering and the mixture model
Gaussian mixture model
Binary data
Categorical variables
Contingency tables
Implementation
Conclusion

2. Model-Based Co-Clustering
Metric approach
Probabilistic models
Latent block model
Maximum likelihood estimation and algorithms
Bayesian approach
Conclusion and miscellaneous developments

3. Co-Clustering of Binary and Categorical Data
Example and notation
Metric approach
Bernoulli latent block model and algorithms
Parsimonious Bernoulli LBMs
Categorical data
Bayesian inference
Model selection
Illustrative experiments
Conclusion

4. Co-Clustering of Contingency Tables
Measures of association
Contingency table associated with a couple of partitions
Co-clustering of contingency table
Model-based co-clustering
Comparison of all algorithms
Conclusion

5. Co-Clustering of Continuous Data
Metric approach
Gaussian latent block model
Illustrative example
Gaussian block mixture model
Numerical experiments
Conclusion

Bibliography

Index

Langue : Anglais

Collection : COMPUTER ENGINEERING SERIES

Lieu d'édition : TORONTO

Localisation : Bibliothèque Campus de Nice

Support : Numérique

Etat : Présent

Propriétaire : Bibliothèque