prikaz prve stranice dokumenta Metoda za automatsko ocjenjivanje testova s ponuđenim odgovorima
No public access
undergraduate thesis
Metoda za automatsko ocjenjivanje testova s ponuđenim odgovorima
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. urn:nbn:hr:168:036698
Engelmann, Otto
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Engelmann, O. (2019). Metoda za automatsko ocjenjivanje testova s ponuđenim odgovorima (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:036698

Engelmann, Otto. "Metoda za automatsko ocjenjivanje testova s ponuđenim odgovorima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:036698

Engelmann, Otto. "Metoda za automatsko ocjenjivanje testova s ponuđenim odgovorima." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2019. https://urn.nsk.hr/urn:nbn:hr:168:036698

Engelmann, O. (2019). 'Metoda za automatsko ocjenjivanje testova s ponuđenim odgovorima', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:036698

Engelmann O. Metoda za automatsko ocjenjivanje testova s ponuđenim odgovorima [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2019 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:036698

O. Engelmann, "Metoda za automatsko ocjenjivanje testova s ponuđenim odgovorima", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2019. Available at: https://urn.nsk.hr/urn:nbn:hr:168:036698

Metadata
TitleMetoda za automatsko ocjenjivanje testova s ponuđenim odgovorima
Title (english)Method for Automatic Evaluation of Tests With Offered Answers
AuthorOtto Engelmann
MentorMarko Subašić (mentor)
Committee memberMarko Subašić (predsjednik povjerenstva)
Committee memberJelena Ivanković (član povjerenstva)
Committee memberDenis Milošević (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2019-07-12, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Automatiziranje postupka ocjenjivanja testova s ponud̄enim odgovorima pomoću dubokih neuronskih mreža. Prvi korak je izgradnja generatora koji stvara proizvo- ljan broj slika testova koje su korištene za treniranje i za evaluaciju neuronskih mreža. Zatim se provodi postupak treniranja neuronskih mreža u kojemu je istrenirano četiri takve mreže. Mreža za pronalaženje područja pitanja, mreža za prepoznavanje labela odgovora, mreža za prepoznavanje labela pitanja i mreža za pronalaženje označenih odgovora. Na kraju je dan prijedlog algoritma koji bi pomoću navedenih mreža ocje- njivao testove.
Abstract (english)
Automation of grading tests with offered answers using deep neural networks. The first step is creating a generator that can create an arbitrary number of test images used for training and evaluating neural networks. After that begins the process of tra- ining neural networks in which four such networks are trained. A network for finding question area, a network for answer labels recognition, a network for question labels recognition and a network for finding marked answers. Finally, algorithm that uses these networks for grading tests is proposed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:036698
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 on2020-01-07 17:51:29