| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:IMPLEMENTACIJA ALGORITMA VZVRATNEGA RAZŠIRJANJA NAPAKE NA GRAFIČNEM PROCESORJU
Authors:ID Bratanović, Alen (Author)
ID Strnad, Damjan (Mentor) More about this mentor... New window
ID Guid, Nikola (Comentor)
Files:.pdf VS_Bratanovic_Alen_2009.pdf (620,93 KB)
MD5: D9F2EB2C458FA02336D349A0CE6338C8
PID: 20.500.12556/dkum/f38eeebf-7bd9-458f-95a5-3f2f4c8a8d77
 
Language:Slovenian
Work type:Undergraduate thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:V diplomskem delu smo predstavili implementacijo algoritma vzvratnega razširjanja napake na GPU. V uvodu predstavimo nevronske mreže, njihovo uporabo, lastnosti in zmogljivosti. Posebej predstavimo idejo algoritma vzvratnega razširjanja napake in opišemo njegove korake izvajanja ter postopek pretvorbe iz serijske v paralelno obliko. Sledi opis nVidia grafične kartice in njene arhitekture. Nato opišemo programski model CUDA, programski vmesnik in principe programiranja v CUDA okolju. Sledi predstavitev programske implementacije algoritma vzvratnega razširjanja napake v CUDA. Na koncu naredimo test in prikažemo dosežene rezultate.
Keywords:nevron, nevronska mreža, algoritem vzvratnega razširjanja napake, paralelno računanje, grafični procesor, CUDA
Place of publishing:Maribor
Publisher:[A. Bratanović]
Year of publishing:2009
PID:20.500.12556/DKUM-11323 New window
UDC:004.8:004.93(043.2)
COBISS.SI-ID:13686550 New window
NUK URN:URN:SI:UM:DK:843BT85V
Publication date in DKUM:10.12.2009
Views:3490
Downloads:291
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:IMPLEMENTATION OF ERROR BACKPROPAGATION ALGORITHM ON GRAPHICAL PROCESSOR
Abstract:In this diploma work we present the implementation of error back-propagation algorithm on GPU. In the introduction we describe neural networks, their usage, properties, and capacities. We present the idea of the error back-propagation algorithm and we describe the steps of the implementation process and the conversion from serial to parallel form. A description of nVidia graphics card and its architecture comes next. Then we describe the CUDA programming model, programming interface, and principles of the CUDA programming environment. After that we report on the software implementation of error back-propagation algorithm in CUDA. We conclude with the presentation of results from practical experiments.
Keywords:neuron, neural network, error backpropagation algorithm, parallel computing, graphical processor, CUDA


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica