izpis_h1_title_alt

Realizacija mehkega inferenčnega stroja v okolju CUDA : diplomsko delo
ID Bricman, Rok (Author), ID Lebar Bajec, Iztok (Mentor) More about this mentor... This link opens in a new window

URLURL - Presentation file, Visit http://eprints.fri.uni-lj.si/2749/ This link opens in a new window

Abstract
Vse procese programsko realiziranega inferenčnega stroja imenujemo mehko procesiranje. Ti procesi so mehčanje vhodnih vrednosti, mehka inferenca ali sklepanje in ostrenje mehke množice, v tem vrstnem redu. Sama izvedba se imenuje mehki inferenčni stroj ali sistem mehke logike. V diplomskem delu je opisan takšen sistem v vzporedni izvedbi po posebnem pristopu, kjer v primerjavi z zaporedno izvedbo kompleksnejše operacije razbijemo na več preprostejših. Za izvedbo smo uporabili arhitekturo CUDA, ki nam omogoča splošno namensko vzporedno računanje s sodobnimi GPE-ji. To izvedbo smo na koncu testirali ter primerjali z zaporedno izvedbo na CPE-ju. Primerjali pa smo tudi natančnost rezultatov in čase operacij algoritmov. Čas je merjen posebej za vse tri glavne procese. Prav tako je merjen tudi skupni čas, ki zajema tudi deklaracije, rezerviranje in kopiranje v pomnilnik. Podatki vhodnih vrednosti in baz znanj so pripravljeni in pridobljeni iz programskih paketov MATLAB in fuzzylite.

Language:Slovenian
Keywords:mehko procesiranje, mehka inferenca, mehčanje, ostrenje, GPE procesiranje, CUDA, računalništvo, visokošolski strokovni študij, računalništvo in informatika, diplomske naloge
Work type:Bachelor thesis/paper
Typology:2.11 - Undergraduate Thesis
Organization:FRI - Faculty of Computer and Information Science
Publisher:[R. Bricman]
Year:2014
Number of pages:28 str.
PID:20.500.12556/RUL-68931 This link opens in a new window
UDC:004.2(043.2)
COBISS.SI-ID:1536028867 This link opens in a new window
Publication date in RUL:10.07.2015
Views:1315
Downloads:230
Metadata:XML RDF-CHPDL DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Implementation of the fuzzy logic inference system in CUDA
Abstract:
All processes in a software implemented inference machine are called fuzzy processes. These processes are fuzzification, fuzzy inference and defuzzification, executed in that order. The implementation itself is called a fuzzy inference machine or a fuzzy logic system. This thesis describes such a system in a parallel implementation with a specific approach, where complex operations are broken down into multiple simpler ones. We used the CUDA architecture, which allows us the usage of general purpose parallel computing on modern GPU’s. At the end we tested this implementation, in comparison with the sequential implementation on the CPU, by comparing the precision of the computational results and the needed times of operation algorithms.

Keywords:fuzzy processing, fuzzy inference, fuzzification, defuzzification, GPU processing, CUDA, computer science, computer and information science, diploma

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back