Mappings of SOM and LVQ on the partial tree shape neurocomputer

Author

Kolinummi, Pasi ; Hämäläinen, Timo ; Kaski, Kimmo

Author_Institution

Tampere Univ. of Technol., Finland

Volume

2

fYear

1997

fDate

9-12 Jun 1997

Firstpage

904

Abstract

Mappings of self-organizing map (SOM) and learning vector quantization (LVQ) networks are presented for a parallel neurocomputer system called PARNEU (partial tree shape neurocomputer). The partial tree shape architecture offers many mapping possibilities at several levels of parallelism for both execution and learning mode. In this paper we present both neuron and weight parallel mapping with online updating scheme. Computational complexity and the time required in each step are considered in order to compare mappings and to find out expected performance. About 8 MCUPS can be achieved with four PUs operating at the frequency of 40 MHz

Keywords

computational complexity; learning (artificial intelligence); neural net architecture; parallel architectures; self-organising feature maps; vector quantisation; PARNEU; computational complexity; learning vector quantization; online updating scheme; partial tree shape architecture; partial tree shape neurocomputer; self-organizing map; Artificial neural networks; Computational complexity; Computer networks; Concurrent computing; Electronic mail; Hardware; Neurons; Parallel processing; Shape control; Workstations;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks,1997., International Conference on

Conference_Location

Houston, TX

Print_ISBN

0-7803-4122-8

Type

conf

DOI

10.1109/ICNN.1997.616145

Filename

616145