An empirical study of neighbourhood decay in Kohonen's self organizing map
Contribuinte(s) |
[Unknown] |
---|---|
Data(s) |
01/01/1999
|
Resumo |
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. |
Identificador | |
Idioma(s) |
eng |
Publicador |
IEEE |
Relação |
http://dro.deakin.edu.au/eserv/DU:30044542/venkatesh-anempirical-1999.pdf http://dx.doi.org/10.1109/IJCNN.1999.832682 |
Direitos |
1999, IEEE |
Palavras-Chave | #algorithm design and analysis #biological processes #biological system modeling #biology computing #brain modeling #geography #graphics #iterative algorithms #performance analysis #performance gain |
Tipo |
Conference Paper |