prikaz prve stranice dokumenta Vizualizacija rada konvolucijske neuronske mreže
  Download
PDF 3.78 MB
undergraduate thesis
Vizualizacija rada konvolucijske neuronske mreže
Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2020. urn:nbn:hr:235:108019
Vlahović, Stjepan
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Cite this document

Vlahović, S. (2020). Vizualizacija rada konvolucijske neuronske mreže (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:108019

Vlahović, Stjepan. "Vizualizacija rada konvolucijske neuronske mreže." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2020. https://urn.nsk.hr/urn:nbn:hr:235:108019

Vlahović, Stjepan. "Vizualizacija rada konvolucijske neuronske mreže." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2020. https://urn.nsk.hr/urn:nbn:hr:235:108019

Vlahović, S. (2020). 'Vizualizacija rada konvolucijske neuronske mreže', Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 25 April 2024, https://urn.nsk.hr/urn:nbn:hr:235:108019

Vlahović S. Vizualizacija rada konvolucijske neuronske mreže [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2020 [cited 2024 April 25] Available at: https://urn.nsk.hr/urn:nbn:hr:235:108019

S. Vlahović, "Vizualizacija rada konvolucijske neuronske mreže", Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:235:108019

Please login to the repository to save this object to your list.
Metadata
TitleVizualizacija rada konvolucijske neuronske mreže
Title (english)Visualizing the work of convolution neural network
AuthorStjepan Vlahović
MentorTomislav Stipančić (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2020-02-28, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Artificial Intelligence
Abstract
U ovom radu će se razvijati modularna aplikacija za vizualizaciju aktivacije slojeva VGG16 konvolucijske neuronske mreže. Prvi dio rada obrađuje teoriju konvolucijskih neuronskih mreža te metode za vizualizaciju i razumijevanje konvolucijskih neuronskih mreža. Nakon toga slijedi dio koji objašnjava kodiranje aplikacije u programu Python. Na kraju se analiziraju rezultati modularne aplikacije, vizualizirani izlazni volumen slojeva konvolucijske neuronske mreže raspoređen u 2D prostoru.
Abstract (english)
In this paper, a modular application will be developed to visualize the activation of VGG16 layers of a convolutional neural network. The first part of the paper deals with the theory of convolution neural networks and methods for visualizing and understanding convolution neural networks. This is followed by the part that explains coding of applications in Python program. Finally, the results of the modular application, a visualized output volume arranged in 2D space, is analyzed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:108019
Study programmeTitle: Mechanical Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
RepositoryRepository of Faculty of Mechanical Engineering and Naval Architecture University of Zagreb
Created on2020-02-24 08:46:41

(©) Nacionalna i sveučilišna knjižnica u Zagrebu 2015. Sva prava pridržana. | Hrvatske bratske zajednice 4 p.p. 550, 10000 Zagreb, Hrvatska Tel. ++ 385 1 616-4040
OIB: 84838770814 | IBAN: HR66 2340 0091 1000 1008 1, Porezni broj (PDV identifikacijski broj) - VAT Number: HR84838770814
Prijava u repozitorij