NEIGHBORHOOD FUNCTION DESIGN FOR EMBEDDING IN REDUCED DIMENSION

Jiun-Wei Liou, Cheng-Yuan Liou

2011

Abstract

LLE(Local linear embedding) is a widely used approach for dimension reduction. The neighborhood selection is an important issue for LLE. In this paper, the e-distance approach and a slightly modified version of k-nn method are introduced. For different types of datasets, different approaches are needed in order to enjoy higher chance to obtain better representation. For some datasets with complex structure, the proposed Ɛ-distance approach can obtain better representations. Different neighborhood selection approaches will be compared by applying them to different kinds of datasets.

Paper Citation

in Harvard Style

Liou J. and Liou C. (2011). NEIGHBORHOOD FUNCTION DESIGN FOR EMBEDDING IN REDUCED DIMENSION . In Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011) ISBN 978-989-8425-84-3, pages 190-195. DOI: 10.5220/0003681201900195

in Bibtex Style

@conference{ncta11,
author={Jiun-Wei Liou and Cheng-Yuan Liou},
title={NEIGHBORHOOD FUNCTION DESIGN FOR EMBEDDING IN REDUCED DIMENSION},
booktitle={Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)},
year={2011},
pages={190-195},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003681201900195},
isbn={978-989-8425-84-3},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Neural Computation Theory and Applications - Volume 1: NCTA, (IJCCI 2011)
TI - NEIGHBORHOOD FUNCTION DESIGN FOR EMBEDDING IN REDUCED DIMENSION
SN - 978-989-8425-84-3
AU - Liou J.
AU - Liou C.
PY - 2011
SP - 190
EP - 195
DO - 10.5220/0003681201900195