prikaz prve stranice dokumenta Raspodijeljeno duboko učenje korištenjem programske knjižnice Keras
No public access
undergraduate thesis
Raspodijeljeno duboko učenje korištenjem programske knjižnice Keras
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. urn:nbn:hr:168:821841
Ibrović, Bernard
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Ibrović, B. (2022). Raspodijeljeno duboko učenje korištenjem programske knjižnice Keras (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:821841

Ibrović, Bernard. "Raspodijeljeno duboko učenje korištenjem programske knjižnice Keras." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:821841

Ibrović, Bernard. "Raspodijeljeno duboko učenje korištenjem programske knjižnice Keras." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2022. https://urn.nsk.hr/urn:nbn:hr:168:821841

Ibrović, B. (2022). 'Raspodijeljeno duboko učenje korištenjem programske knjižnice Keras', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 03 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:821841

Ibrović B. Raspodijeljeno duboko učenje korištenjem programske knjižnice Keras [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2022 [cited 2024 July 03] Available at: https://urn.nsk.hr/urn:nbn:hr:168:821841

B. Ibrović, "Raspodijeljeno duboko učenje korištenjem programske knjižnice Keras", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2022. Available at: https://urn.nsk.hr/urn:nbn:hr:168:821841

Metadata
TitleRaspodijeljeno duboko učenje korištenjem programske knjižnice Keras
Title (english)Distributed Deep Learning using Keras
AuthorBernard Ibrović
MentorKrešimir Pripužić (mentor)
Committee memberKrešimir Pripužić (predsjednik povjerenstva)
Committee memberJosip Marić (član povjerenstva)
Committee memberPetar Krivić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2022-09-02, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Rad se bavi proučavanjem dubokog učenja i umjetnih neuronskih mreža u kontekstu programske knjižnice Keras te načinima korištenja programske knjižnice Keras u centraliziranom i raspodijeljenom okruženju. Nakon teorijskog uvoda, slijedi praktičan dio gdje je na konkretnom primjeru opisan način izgradnje umjetne neuronske mreže te njeno treniranje, a zatim i provjera točnosti na novim podacima. Navedene su razlike u kodu te razlike u performansama između centraliziranog i raspodijeljenog okruženja.
Abstract (english)
Thesis considers deep learning and artificial neural networks in the context of software library Keras, along with the usage of software library Keras in centralized and distributed environment. After theoretical introduction, there is a practical part where on a given example the process of building an artificial neural network, it's training and accuracy testing are performed. The practical part also compares the differences in code as well as the differences in the performance in centralized and distributed environment.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:821841
Study programmeTitle: Computing
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2023-01-15 10:19:58