Episodic Clustering of Data Streams Using a Topology-Learning Neural Network

Titelaufnahme

Titel
Episodic Clustering of Data Streams Using a Topology-Learning Neural Network
Verfasser
Tscherepanow, Marko ; Kühnel, Sina ; Riechers, Sören
Herausgeber
Lemaire, Vincent ; Lamirel, Jean-Charles ; Cuxac, Pascal
Erschienen
2012
Sprache
Englisch
Dokumenttyp
Konferenzband
Schlagwörter
Adaptive Resonance Theory / On-line learning / TopoART / Episodic memory / Incremental learning / Clustering / Neural networks
URN
urn:nbn:de:0070-pub-25192218

Zugriffsbeschränkung

Links

Dateien

Klassifikation

Abstract

In this paper, an extension of the unsupervised topology-learning TopoART neural network is presented. Like TopoART, it is capable of stable incremental on-line clustering of real-valued data. However, it incorporates temporal information in such a way that consecutive input vectors with a low distance in the input space are summarised to episode-like clusters. Inspired by natural memory systems, we propose two recall methods enabling the selection and retrieval of these episodes. They are demonstrated at the example of a video stream recorded in a natural environment.

Statistik