Title :
An empirical study of neighbourhood decay in Kohonen´s self organising map
Author :
Keith-Magee, Russell ; Venkatesh, Svetha ; Takatsuka, Masahiro
Author_Institution :
Sch. of Comput., Curtin Univ. of Technol., Perth, WA, Australia
Abstract :
In this paper, empirical results are presented which suggest that size and rate of decay of region size plays a much more significant role in the learning, and especially the development of topographic feature maps. Using these results as a basis, a scheme for decaying region size during SOM training is proposed. The proposed technique provides near optimal training time. This scheme avoids the need for sophisticated learning gain decay schemes, and precludes the need for a priori knowledge of likely training times. This scheme also has some potential uses for continuous learning
Keywords :
curve fitting; learning (artificial intelligence); optimisation; self-organising feature maps; topology; Kohonen self organising map; SOM learning; continuous learning; decaying region size; gain decay; goodness of fit; neighbourhood decay; optimisation; topographic feature maps; Algorithm design and analysis; Biological processes; Biological system modeling; Biology computing; Brain modeling; Geography; Graphics; Iterative algorithms; Performance analysis; Performance gain;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.832682