Title :
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
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;
Conference_Titel :
Neural Networks,1997., International Conference on
Conference_Location :
Houston, TX
Print_ISBN :
0-7803-4122-8
DOI :
10.1109/ICNN.1997.616145
