Methodology of building intelligent systems on parallel processor

2014

Closed access Metadata (CSL-JSON)
DOI 10.1109/icaict.2014.7035973
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

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.