L1正則化を用いたエントロピー型可能性クラスタリングについて

濵砂 幸裕; 遠藤 靖典

doi:10.14864/fss.29.0_19

29th Fuzzy System Symposium

Session ID : MB2-4

DOI https://doi.org/10.14864/fss.29.0_19

Conference information

Host: Japan Society for Fuzzy Theory and Intelligent Informatics (SOFT)

main

On Entropy Based Possibilistic Clustering with L₁-Regularization

*Yukihiro Hamasuna, Yasunori Endo

Author information

Keywords: possibilistic clustering, crisp possibilistic clustering, L₁-regularization, sequential extraction

CONFERENCE PROCEEDINGS FREE ACCESS

Details

Abstract

Possibilistic clustering is well-known as one of the useful techniques because it is robust against noise in data. We propose entropy based possibilistic clustering with L1-regularization and show its classification function. We, moreover, show the result of sequential extraction by proposed method.

Corresponding author

Register with J-STAGE for free!