Conference paper
Discovering hierarchical structure in normal relational data
Hierarchical clustering is a widely used tool for structuring and visualizing complex data using similarity. Traditionally, hierarchical clustering is based on local heuristics that do not explicitly provide assessment of the statistical saliency of the extracted hierarchy. We propose a non-parametric generative model for hierarchical clustering of similarity based on multifurcating Gibbs fragmentation trees.
This allows us to infer and display the posterior distribution of hierarchical structures that comply with the data. We demonstrate the utility of our method on synthetic data and data of functional brain connectivity.
| Language: | English |
|---|---|
| Publisher: | IEEE |
| Year: | 2014 |
| Pages: | 1-6 |
| Proceedings: | 4th International Workshop on Cognitive Information Processing (CIP 2014) |
| ISBN: | 1479936960 , 1479936979 , 9781479936960 and 9781479936977 |
| ISSN: | 23271698 and 23271671 |
| Types: | Conference paper |
| DOI: | 10.1109/CIP.2014.6844498 |
| ORCIDs: | Schmidt, Mikkel Nørgaard , Herlau, Tue and Mørup, Morten |
Bioengineering Communication, Networking and Broadcast Technologies Computing and Processing Robotics and Control Systems Signal Processing and Analysis
Clustering algorithms Computational modeling Correlation Couplings Data models Gaussian distribution Image color analysis complex data structure complex data visualization data structures data visualisation extracted hierarchy functional brain connectivity data hierarchical clustering hierarchical structure discovery local heuristics multifurcating Gibbs fragmentation trees nonparametric generative model nonparametric statistics normal relational data pattern clustering posterior distribution statistical saliency assessment structural similarity synthetic data unsupervised learning unsupervised learning method
