DocumentCode :
350983
Title :
Self-organization in the SOM with a decreasing neighborhood function of any width
Author :
Flanagan, John A.
Author_Institution :
Neural Networks Res. Centre, Helsinki Univ. of Technol., Espoo, Finland
Volume :
1
fYear :
1999
fDate :
1999
Firstpage :
156
Abstract :
A proof of self-organization for a general one dimensional SOM (i.e., one dimensional array of neurons, one dimensional input) with a strictly monotonically decreasing neighborhood function of any width W is given. The proof is not dependent on any particular type of probability distribution of the input but rather minimum conditions that the distribution must satisfy are specified. For a total of N neurons the degree (n) of the SOM is defined here as n=N div W+1 when N mod W≠0 or else n=N/W. It is shown that a total of 2n intervals of nonzero probability on the support of the input, separated by distances which depend on parameters of the SOM are sufficient for self-organization
Keywords :
self-organising feature maps; SOM; decreasing neighborhood function; probability distribution; self organizing map; self-organization;
fLanguage :
English
Publisher :
iet
Conference_Titel :
Artificial Neural Networks, 1999. ICANN 99. Ninth International Conference on (Conf. Publ. No. 470)
Conference_Location :
Edinburgh
ISSN :
0537-9989
Print_ISBN :
0-85296-721-7
Type :
conf
DOI :
10.1049/cp:19991101
Filename :
819558
Link To Document :
بازگشت