A Novel Stability based Feature Selection Framework for k-means Clustering thumbnail
Pause
Mute
Subtitles
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

A Novel Stability based Feature Selection Framework for k-means Clustering

Published on Oct 03, 20113282 Views

Stability of a learning algorithm with respect to small input perturbations is an important property, as it implies the derived models to be robust with respect to the presence of noisy features and

Related categories

Chapter list

A Novel Stability based Feature Selection Framework for k-means Clustering00:00
Presentation outline00:22
What's new00:51
k-means and PCA01:55
Feature selection and Sparse PCA03:23
Stability of PCA04:35
Stability maximizing sparse PCA05:37
Algorithm10:40
Deflation for multiple eigenvectors11:26
Empirical results11:46
Clustering (1)12:54
Clustering (2)13:56
Clustering (3)14:03
Clustering (4)14:09
Qualitative evaluation14:11
Further work15:35
Algorithmic approach16:41