Conference paper
Modelling dense relational data
Relational modelling classically consider sparse and discrete data. Measures of influence computed pairwise between temporal sources naturally give rise to dense continuous-valued matrices, for instance p-values from Granger causality. Due to asymmetry or lack of positive definiteness they are not naturally suited for kernel K-means.
We propose a generative Bayesian model for dense matrices which generalize kernel K-means to consider off-diagonal interactions in matrices of interactions, and demonstrate its ability to detect structure on both artificial data and two real data sets.
Language: | English |
---|---|
Publisher: | IEEE |
Year: | 2012 |
Pages: | 1-6 |
Proceedings: | 2012 IEEE International Workshop on Machine Learning for Signal Processing |
Series: | Machine Learning for Signal Processing |
ISBN: | 1467310247 , 9781467310246 , 1467310255 , 1467310263 , 9781467310253 and 9781467310260 |
ISSN: | 21610363 and 15512541 |
Types: | Conference paper |
DOI: | 10.1109/MLSP.2012.6349747 |
ORCIDs: | Herlau, Tue , Mørup, Morten , Schmidt, Mikkel Nørgaard and Hansen, Lars Kai |
Artificial neural networks Bayesian model Computational modeling Correlation Data models Granger causality Kernel Silicon Vectors artificial data belief networks biomedical MRI dense continuous-valued matrices dense matrices dense relational data fMRI instance p-values kernel K-means matrix algebra pattern clustering positive definiteness real data sets relational modelling