prikaz prve stranice dokumenta Prepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja
No public access
undergraduate thesis
Prepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. urn:nbn:hr:168:160450
Domović, Dominik
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Domović, D. (2017). Prepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:160450

Domović, Dominik. "Prepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. https://urn.nsk.hr/urn:nbn:hr:168:160450

Domović, Dominik. "Prepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2017. https://urn.nsk.hr/urn:nbn:hr:168:160450

Domović, D. (2017). 'Prepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 16 August 2024, https://urn.nsk.hr/urn:nbn:hr:168:160450

Domović D. Prepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2017 [cited 2024 August 16] Available at: https://urn.nsk.hr/urn:nbn:hr:168:160450

D. Domović, "Prepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:168:160450

Metadata
TitlePrepoznavanje neispravnih lemnih spojeva upotrebom strojnog učenja
Title (english)Detecting Soldering Defects by Machine Learning
AuthorDominik Domović
MentorVladimir Čeperić (mentor)
Committee memberVladimir Čeperić (predsjednik povjerenstva)
Committee memberIvan Filković (član povjerenstva)
Committee memberMarko Magerl (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2017-07-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Ovaj rad je objasnio ideju umjetnih neuronskih mreža i njihovu primjenu, fokusirajući se na konvolucijske neuronske mreže. Razvijena je jednostavna implementacija konvolucijske mreže, koja je trenirana na skupu podataka od 305 sličica lemnih spojeva. Opisan je postupak izvođenja programa i analizirani su dobiveni rezultati. Zaključeno je da je naučena mreža uspješno obavila svoju namjenu, rezultirajući s visokim postotkom točnog predviđanja.
Abstract (english)
This work has explained the idea of artificial neural networks and their application, focusing on convolutional neural networks. A simple implementation of a convolutional network has been developed, which has been trained on a dataset of 305 images of solder joints. The process of program staging has been explained and the computed data has been analyzed. The trained network was successful in detecting soldering defects, resulting in high percentage of correct predictions.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:160450
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 on2019-03-13 19:58:16