A Hierarchical ART Network for the Stable Incremental Learning of Topological Structures and Associations from Noisy Data

Tscherepanow M, Kortkamp M, Kammer M (2011)
Neural Networks 24(8): 906-916.

Download
Campus/VPN tscherepanow.marko2011ahierarchical-nn-r1.pdf
Zeitschriftenaufsatz | Veröffentlicht | Englisch
Abstract / Bemerkung
In this article, a novel unsupervised neural network combining elements from Adaptive Resonance Theory and topology-learning neural networks is presented. It enables stable on-line clustering of stationary and non-stationary input data by learning their inherent topology. Here, two network components representing two different levels of detail are trained simultaneously. By virtue of several filtering mechanisms, the sensitivity to noise is diminished, which renders the proposed network suitable for the application to real-world problems. Furthermore, we demonstrate that this network constitutes an excellent basis to learn and recall associations between real-world associative keys. Its incremental nature ensures that the capacity of the corresponding associative memory fits the amount of knowledge to be learnt. Moreover, the formed clusters efficiently represent the relations between the keys, even if noisy data is used for training. In addition, we present an iterative recall mechanism to retrieve stored information based on one of the associative keys used for training. As different levels of detail are learnt, the recall can be performed with different degrees of accuracy.
Erscheinungsjahr
Zeitschriftentitel
Neural Networks
Band
24
Zeitschriftennummer
8
Seite
906-916
ISSN
PUB-ID

Zitieren

Tscherepanow M, Kortkamp M, Kammer M. A Hierarchical ART Network for the Stable Incremental Learning of Topological Structures and Associations from Noisy Data. Neural Networks. 2011;24(8):906-916.
Tscherepanow, M., Kortkamp, M., & Kammer, M. (2011). A Hierarchical ART Network for the Stable Incremental Learning of Topological Structures and Associations from Noisy Data. Neural Networks, 24(8), 906-916. doi:10.1016/j.neunet.2011.05.009
Tscherepanow, M., Kortkamp, M., and Kammer, M. (2011). A Hierarchical ART Network for the Stable Incremental Learning of Topological Structures and Associations from Noisy Data. Neural Networks 24, 906-916.
Tscherepanow, M., Kortkamp, M., & Kammer, M., 2011. A Hierarchical ART Network for the Stable Incremental Learning of Topological Structures and Associations from Noisy Data. Neural Networks, 24(8), p 906-916.
M. Tscherepanow, M. Kortkamp, and M. Kammer, “A Hierarchical ART Network for the Stable Incremental Learning of Topological Structures and Associations from Noisy Data”, Neural Networks, vol. 24, 2011, pp. 906-916.
Tscherepanow, M., Kortkamp, M., Kammer, M.: A Hierarchical ART Network for the Stable Incremental Learning of Topological Structures and Associations from Noisy Data. Neural Networks. 24, 906-916 (2011).
Tscherepanow, Marko, Kortkamp, Marco, and Kammer, Marc. “A Hierarchical ART Network for the Stable Incremental Learning of Topological Structures and Associations from Noisy Data”. Neural Networks 24.8 (2011): 906-916.
Volltext(e)
Name
tscherepanow.marko2011ahierarchical-nn-r1.pdf
Access Level
Campus/VPN UniBi Only
Zuletzt Hochgeladen
2014-06-20T13:02:23Z

Link(s) zu Volltext(en)
Access Level
Restricted Closed Access

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Web of Science

Dieser Datensatz im Web of Science®

Quellen

PMID: 21704496
PubMed | Europe PMC

Suchen in

Google Scholar