An Extended TopoART Network for the Stable On-Line Learning of Regression Functions

Titelaufnahme

Titel
An Extended TopoART Network for the Stable On-Line Learning of Regression Functions
Verfasser
Tscherepanow, Marko
Herausgeber
Lu, Bao-Liang ; Zhang, Liqing ; Kwok, James
Erschienen
2011
Sprache
Englisch
Dokumenttyp
Konferenzband
Schlagwörter
On-line learning / Adaptive Resonance Theory / Regression / TopoART
ISBN
978-3-642-24958-7
URN
urn:nbn:de:0070-pub-23011919
DOI
10.1007/978-3-642-24958-7_65

Zugriffsbeschränkung

Links

Dateien

Klassifikation

Abstract

In this paper, a novel on-line regression method is presented. Due to its origins in Adaptive Resonance Theory neural networks, this method is particularly well-suited to problems requiring stable incremental learning. Its performance on five publicly available datasets is shown to be at least comparable to two established off-line methods. Furthermore, it exhibits considerable improvements in comparison to its closest supervised relative Fuzzy ARTMAP.

Inhalt

Statistik