Abstract
This paper presents a recurrent self-organizing map (RSOM) for temporal sequence processing. The RSOM uses the history of a pattern (i.e., the previous elements in the sequence) to compute the best matching unit and to adapt the weights of the map. The RSOM is similar to Kohonen's original SOM except that each unit has an associated recursive differential equation. The experimental results show that the RSOM is able to learn and distinguish temporal sequences, and that it can improve EEG-based epileptic activity detection.
Preview
Unable to display preview. Download preview PDF.
References
G.J. Chappell & J.G. Taylor (1993). Neural Networks, 6:441–445.
N.A. Gershenfeld & A.S. Weigend (1993). In Times Series Prediction: Forecasting the Future and Understanding the Past, pp. 1–70, Addison-Wesley.
J. Kangas (1991). ICANN'91, pp. 1591–1594.
J. Kangas (1994). Dr. Tech. thesis, Helsinki University of Technology.
T. Kohonen (1991). ICANN'91, pp. 1357–1360.
T. Kohonen (1993). Proc. IEEE Int. Conf. on Neural Networks, pp. 1147–1156.
T. Kohonen (1995). Self-Organizing Maps. Springer-Verlag.
L. Leinonen, J. Kangas, K. Torkkola, & A. Juvas (1992). Journal of Speech and Hearing Research, 35:287–295.
S.P. Luttrell (1989). Pattern Recognition Letters, 10:1–7.
S.G. Mallat (1989). IEEE Trans. Pattern Anal. Machine Intell., 11:674–693.
M.C. Mozer (1993). In Times Series Prediction: Forecasting the Future and Understanding the Past, pp. 243–264, Addison-Wesley.
J.G. Proakis & D.G. Manolakis (1992). Digital Signal Processing. Macmillan.
A.C. Tsoi & A.D. Black (1994). IEEE Trans. on Neural Networks, 5:229–239.
M. Varsta, J. Heikkonen, & J. del R. Millân (1997). Int. Conf. on Engineering Applications of Neural Networks.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Varstal, M., Millán, J.d.R., Heikkonen, J. (1997). A recurrent self-organizing map for temporal sequence processing. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020191
Download citation
DOI: https://doi.org/10.1007/BFb0020191
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive