Temporal Hebbian Self-Organizing Map for Sequences

In this paper we present a new self-organizing neural network called Temporal Hebbian Self-organizing Map (THSOM) suitable for modelling of temporal sequences. The network is based on Kohonen's Self-organizing Map, which is extended with a layer of full recurrent connections among the neurons. The layer of recurrent connections is trained with Hebb's rule. The recurrent layer represents temporal order of the input vectors. The THSOM brings a straightforward way of embedding context information in recurrent SOM using neurons with Euclidean metric and scalar product. The recurrent layer can be easily converted into a stochastic automaton (Markov Chain) generating sequences used for previous THSOM training. Finally, two real world examples of THSOM usage are presented. THSOM was applied to extraction of road network from GPS data and to construction of spatio-temporal models of spike train sequences measured in human brain in vivo.

[1]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[2]  M. Delong,et al.  Surgery for Parkinson's disease. , 1997, Journal of neurology, neurosurgery, and psychiatry.

[3]  Jukka Heikkonen,et al.  Temporal sequence processing using recurrent SOM , 1998, 1998 Second International Conference. Knowledge-Based Intelligent Electronic Systems. Proceedings KES'98 (Cat. No.98EX111).

[4]  Jouko Lampinen,et al.  Analytical comparison of the Temporal Kohonen Map and the Recurrent Self Organizing Map , 2000, ESANN.

[5]  Thomas Voegtlin,et al.  Context quantization and contextual self-organizing maps , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[6]  K. Mewes,et al.  The subthalamic nucleus in Parkinson's disease: somatotopic organization and physiological characteristics. , 2001, Brain : a journal of neurology.

[7]  Thomas Voegtlin,et al.  Recursive self-organizing maps , 2002, Neural Networks.

[8]  Markus Varsta,et al.  Self-organizing maps in sequence processing , 2002 .

[9]  Marc Strickert,et al.  Neural Gas for Sequences , 2003 .

[10]  Jan Koutník,et al.  Neural Network Generating Hidden Markov Chain , 2005 .

[11]  Alessio Micheli,et al.  Self-Organizing Maps for Time Series , 2005 .

[12]  Young-Seuk Park,et al.  Self-Organizing Map , 2008 .