Analysis of models of representation for expert choice neuroprocessor structure

The analysis of the representation of the expert system for selecting the structure of multiprocessor systems (MPS) is performed. Algorithms of three different models of the interface representation of expert systems are described on the basis of the method of parallelizing is proposed by the author...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2018 7th Mediterranean Conference on Embedded Computing (MECO) s. 1 - 4
Hlavní autori: Ruchkin, Vladimir, Fulin, Vladimir, Pikulin, Dmitry, Kostrov, Boris, Taganov, Aleksandr, Kolesenkov, Aleksandr, Ruchkina, Ekaterina
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.06.2018
Predmet:
analysis of multiprocessor structures
Analytical models
Computational modeling
ComputerSystemStructure class
decision making
expert system interface
Expert systems
getStructureType method
Information exchange
Parallel processing
Pipelines
superset of JavaScript language
Task analysis
Type-Script language
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The analysis of the representation of the expert system for selecting the structure of multiprocessor systems (MPS) is performed. Algorithms of three different models of the interface representation of expert systems are described on the basis of the method of parallelizing is proposed by the authors for the purpose of analyzing possible multiprocessor structures. The program for implementing the interface in the modern language TypeScript is being developed. The ComputerSystemStructure class, the getStructureType method, and some methods for defining structures are presented to describe the characteristic possible MPS structures that identify the type of neural computer network under uncertain conditions using fuzzy sets through neural networks.
DOI:10.1109/MECO.2018.8406043