Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories

Tscherepanow, Marko

Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories

Tscherepanow M (2012)
In: Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM). Perner P (Ed); Fockendorf, Germany: ibai-publishing: 22-34.

Konferenzbeitrag | Veröffentlicht | Englisch

Download

tscherepanow.marko2012incremental-ICDM.pdf

URN

urn:nbn:de:0070-pub-24989977

Autor*in

Tscherepanow, Marko^UniBi

Herausgeber*in

Perner, Petra

Einrichtung

Technische Fakultät > AG Angewandte Informatik
Center of Excellence - Cognitive Interaction Technology CITEC

Abstract / Bemerkung

Incremental on-line learning is an important branch of machine learning. One class of approaches particularly well-suited to such tasks are Adaptive Resonance Theory (ART) neural networks. This paper presents a novel ART network combining the ability of noise-insensi\-tive, incremental clustering and topology learning at different levels of detail from TopoART with Euclidean similarity measures and hyperspherical categories from Hypersphere ART. As a result of the modified internal representations, several limitations of the original TopoART network are lifted. In particular, the presented network can process arbitrarily scaled values even if their range is not entirely known in advance.

Stichworte

Incremental learning; Hierarchical clustering; TopoART; Adaptive Resonance Theory; On-line learning

Erscheinungsjahr

2012

Titel des Konferenzbandes

Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM)

Seite(n)

22-34

Konferenz

Industrial Conference on Data Mining (ICDM)

Konferenzort

Berlin, Germany

Konferenzdatum

2012-07-13

ISBN

978-3-942952-17-0

ISSN

1864-9734

Page URI

https://pub.uni-bielefeld.de/record/2498997

Zitieren

Tscherepanow M. Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories. In: Perner P, ed. Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM). Fockendorf, Germany: ibai-publishing; 2012: 22-34.

Tscherepanow, M. (2012). Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories. In P. Perner (Ed.), Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM) (pp. 22-34). Fockendorf, Germany: ibai-publishing.

Tscherepanow, Marko. 2012. “Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories”. In Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM), ed. Petra Perner, 22-34. Fockendorf, Germany: ibai-publishing.

Tscherepanow, M. (2012). “Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories” in Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM), Perner, P. ed. (Fockendorf, Germany: ibai-publishing), 22-34.

Tscherepanow, M., 2012. Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories. In P. Perner, ed. Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM). Fockendorf, Germany: ibai-publishing, pp. 22-34.

M. Tscherepanow, “Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories”, Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM), P. Perner, ed., Fockendorf, Germany: ibai-publishing, 2012, pp.22-34.

Tscherepanow, M.: Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories. In: Perner, P. (ed.) Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM). p. 22-34. ibai-publishing, Fockendorf, Germany (2012).

Tscherepanow, Marko. “Incremental On-line Clustering with a Topology-Learning Hierarchical ART Neural Network Using Hyperspherical Categories”. Poster and Industry Proceedings of the Industrial Conference on Data Mining (ICDM). Ed. Petra Perner. Fockendorf, Germany: ibai-publishing, 2012. 22-34.

Alle Dateien verfügbar unter der/den folgenden Lizenz(en):

Copyright Statement: