Inexact MDL for linear manifold clusters

We present a regularization technique based on the minimum description length (MDL) principle for the linear manifold clustering. We suggest an inexact minimum description length method based on describing the data structure as linear manifold clusters. We examine the behavior of the proposed method...

Full description

Saved in:

Bibliographic Details
Published in:	2016 23rd International Conference on Pattern Recognition (ICPR) pp. 1345 - 1351
Main Authors:	Haralick, Robert M., Diky, Art, Xing Su, Kiang, Nancy Y.
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-12-2016
Subjects:	Clustering algorithms Data models Encoding Entropy Histograms Manifolds Prototypes
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	We present a regularization technique based on the minimum description length (MDL) principle for the linear manifold clustering. We suggest an inexact minimum description length method based on describing the data structure as linear manifold clusters. We examine the behavior of the proposed method and compare it performance against simulated clustering results of various dimensionality and structure. Finally, we empirically evaluate the proposed technique on a climate data.
DOI:	10.1109/ICPR.2016.7899824