The capacity of a clustering model can be defined as the ability to represent complex spatial data distributions. We introduce a method to quantify the capacity of an approximate spectral clustering model based on the eigenspectrum of the similarity matrix, providing the ability to measure capacity in a direct way and to estimate the most suitable model parameters. The method is tested on simple datasets and applied to a forged banknote classification problem.
Measuring clustering model complexity / S. Rovetta, F. Masulli, A. Cabri (LECTURE NOTES IN COMPUTER SCIENCE). - In: Artificial Neural Networks and Machine Learning – ICANN 2017 / [a cura di] A. Lintas, S. Rovetta, P.F.M.J. Verschure, A.E.P. Villa. - [s.l] : Springer Verlag, 2017. - ISBN 9783319686110. - pp. 434-441 (( Intervento presentato al 26. convegno International Conference on Artificial Neural Networks tenutosi a Alghero nel 2017 [10.1007/978-3-319-68612-7_49].
Measuring clustering model complexity
A. Cabri
2017
Abstract
The capacity of a clustering model can be defined as the ability to represent complex spatial data distributions. We introduce a method to quantify the capacity of an approximate spectral clustering model based on the eigenspectrum of the similarity matrix, providing the ability to measure capacity in a direct way and to estimate the most suitable model parameters. The method is tested on simple datasets and applied to a forged banknote classification problem.File | Dimensione | Formato | |
---|---|---|---|
2017-icann2017-Complexity.pdf
accesso riservato
Tipologia:
Publisher's version/PDF
Dimensione
1.67 MB
Formato
Adobe PDF
|
1.67 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.