Abstract : In order to solve the local convergence problem of the Cross Entropy Clustering algorithm, a split-and-merge operation is introduced to escape from local minima and reach a better solution. We describe the theoretical aspects of the method in a limited space, present a few strategies of tweaking the clustering algorithm and compare them with existing solutions. The experiments show that the presented approach increases flexibility and effectiveness of the whole algorithm.
https://hal.inria.fr/hal-01656257 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Tuesday, December 5, 2017 - 2:59:27 PM Last modification on : Tuesday, December 7, 2021 - 3:33:15 PM
Krzysztof Hajto, Konrad Kamieniecki, Krzysztof Misztal, Przemysław Spurek. Split-and-merge Tweak in Cross Entropy Clustering. 16th IFIP International Conference on Computer Information Systems and Industrial Management (CISIM), Jun 2017, Bialystok, Poland. pp.193-204, ⟨10.1007/978-3-319-59105-6_17⟩. ⟨hal-01656257⟩