Temporal sequence processing using recurrent SOM

Author

Koskela, Timo ; Varsta, Markus ; Heikkonen, Jukka ; Kaski, Kimmo

Author_Institution

Lab. of Comput. Eng., Helsinki Univ. of Technol., Espoo, Finland

Volume

1

fYear

1998

fDate

21-23 Apr 1998

Firstpage

290

Abstract

Recurrent self-organizing map (RSOM) is studied in temporal sequence processing. RSOM includes a recurrent difference vector in each unit of the map, which allows storing temporal context from consecutive input vectors fed to the map. RSOM is a modification of the temporal Kohonen map (TKM). It is shown that RSOM learns a correct mapping from temporal sequences of a simple synthetic data, while TKM fails to learn this mapping. In addition, two case studies are presented, in which RSOM is applied to EEG based epileptic activity detection and to time series prediction with local models. Results suggest that RSOM can be efficiently used in temporal sequence processing

Keywords

recurrent neural nets; self-organising feature maps; time series; EEG based epileptic activity detection; RSOM; TKM; input vectors; recurrent SOM; recurrent difference vector; recurrent self-organizing map; temporal Kohonen map; temporal context; temporal sequence processing; temporal sequences; time series prediction; Delay lines; Difference equations; Electroencephalography; Epilepsy; Information analysis; Laboratories; Neural networks; Predictive models; Supervised learning; Unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Knowledge-Based Intelligent Electronic Systems, 1998. Proceedings KES '98. 1998 Second International Conference on

Conference_Location

Adelaide, SA

Print_ISBN

0-7803-4316-6

Type

conf

DOI

10.1109/KES.1998.725861

Filename

725861