A growing parallel self-organizing map for unsupervised learning

Author

Valova, Iren ; Szer, Daniel ; Georgieva, Natacha

Author_Institution

Dept. of Comput. & Inf. Sci., Univ. of Massachusetts Dartmouth, North Dartmouth, MA, USA

Volume

2

fYear

2002

fDate

6/24/1905 12:00:00 AM

Firstpage

1924

Lastpage

1929

Abstract

SOM approximates a high dimensional unknown input distribution with lower dimensional neural network structure to model the topology of the input space as closely as possible. We present a SOM that processes the whole input in parallel and organizes itself over time. This way, networks can be developed that do not reorganize their structure from scratch every time a new set of input vectors is presented but rather adjust their internal architecture in accordance with previous mappings

Keywords

parallel architectures; probability; self-organising feature maps; unsupervised learning; SOM; growing parallel self-organizing map; high dimensional unknown input distribution; internal architecture; lower dimensional neural network structure; unsupervised learning; Computer networks; Computer science; Counting circuits; Distributed computing; Educational institutions; Euclidean distance; Information science; Network topology; Neural networks; Unsupervised learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on

Conference_Location

Honolulu, HI

ISSN

1098-7576

Print_ISBN

0-7803-7278-6

Type

conf

DOI

10.1109/IJCNN.2002.1007813

Filename

1007813