DocumentCode
263971
Title
Methodology of building intelligent systems on parallel processor
Author
Seitkulov, Yerzhan ; Tokhtabayev, Amur ; Atanov, Sabyrzhan ; Verenik, Nikolai L. ; Girel, Alexey I. ; Tatur, Mikhail M.
Author_Institution
L.N. Gumilyov Eurasian Nat. Univ., Astana, Kazakhstan
fYear
2014
fDate
15-17 Oct. 2014
Firstpage
1
Lastpage
5
Abstract
In the current paper the original interpretation of cognitive process as the totality of clustering tasks, classification and the search of associations was illustrated, as well as it was given the definition of these notions. The similarity of computation graphs for general solution schemes allows to speak about the opportunity of making an unified methodology of building intelligence application systems. The article includes the description of a given original methodology. The architecture of computational system core on the basis of vector processor was examined, it was given the description of data format, tasks system format, and also the general principals of processor functionality. The realization of computing system on the basis of GPU was examined in the paper.
Keywords
cognitive systems; graphics processing units; parallel processing; pattern classification; pattern clustering; vector processor systems; GPU; classification task; clustering task; cognitive process; computation graph; intelligent system; parallel processor; vector processor; Algorithm design and analysis; Clustering algorithms; Computer architecture; Computers; Graphics processing units; Hardware; Semantics; ASIP; Cognitive; intelligent; massive parallel processing; methodology; parallel computing; semantic; vector processor;
fLanguage
English
Publisher
ieee
Conference_Titel
Application of Information and Communication Technologies (AICT), 2014 IEEE 8th International Conference on
Conference_Location
Astana
Print_ISBN
978-1-4799-4120-9
Type
conf
DOI
10.1109/ICAICT.2014.7035973
Filename
7035973
Link To Document