A Generative Dyadic Aspect Model for Evidence Accumulation Clustering thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

A Generative Dyadic Aspect Model for Evidence Accumulation Clustering

Published on Oct 17, 20113081 Views

Evidence accumulation clustering (EAC) is a clustering combination method in which a pair-wise similarity matrix (the so-called co-association matrix) is learnt from a clustering ensemble. This co-ass

Related categories

Chapter list

A Generative Dyadic Model for Evidence Accumulation Clustering00:00
Outline00:29
Clustering Ensembles01:14
Evidence Accumulation Clustering (EAC)02:02
Dyadic Data Analysis03:15
Dyadic Data and Co-Occurrence Matrix03:52
Generative Model05:26
Mixture Model - 106:54
Mixture Model - 207:17
Mixture Model - 307:59
Maximum Likelihood Estimate09:03
E-Step09:27
M-Step09:57
Interpretation of the estimates11:23
Experimental Setup12:21
Example12:46
Results13:22
Conclusions14:07
Acknowledgements15:15