Proceedings of the Japan Joint Automatic Control Conference
THE 53RD JAPAN JOINT AUTOMATIC CONTROL CONFERENCE
Session ID : 502
Conference information

Neuro, Fuzzy and Reinforcement Learning
On Regularization Effects of Membership Fuzzification in Cluster Analysis
Katsuhiro Honda*Yui MatsumotoAkira NotsuHidetomo Ichihashi
Author information
CONFERENCE PROCEEDINGS FREE ACCESS

Details
Abstract
Fuzzy clustering is an active research field, in which cluster structures are flexibly analyzed by using fuzzy memberships. Through a comparative study, this paper discusses that some fuzzification methods also have the effect of regularizing objective functions and contribute to avoiding the initialization problem.
Content from these authors
© 2010 JSME
Previous article Next article
feedback
Top