Community Research and Development Information Service - CORDIS

Abstract

This paper compares two approaches to temporal sequence processing based on Self-Organizing Maps (SOM), namely the Recuurent Self-Organizing Map (RSOM) and the Temporal Kohonen Map (TKM). The convergence properties of these algorithms are studied, and their difference in learning is emphasized both theoretically and with simulations. The results show that RSOM is superior to TKM.

Additional information

Authors: VARSTA M, Helsinki University of Technology (IS);HEIKKONEN J, Helsinki University of Technology (IS);LAMPINEN J, Helsinki University of Technology (IS);MILLAN J R, Istitute for Systems, Informatics and Safety, SoftwareTechnologies and Automation Unit (IT)
Bibliographic Reference: Paper presented: 8th International Conference on Artificial Neural Networks, Skoerde (SE), September 1-4th, 1998
Availability: Available from DG XIII D-2 as Paper EN 41783 ORA
Record Number: 199910209 / Last updated on: 1999-03-12
Category: PUBLICATION
Original language: en
Available languages: en