prikaz prve stranice dokumenta Prepoznavanje znakova korištenjem TensorFlow biblioteke
No public access
undergraduate thesis
Prepoznavanje znakova korištenjem TensorFlow biblioteke
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:503066
Vodopija, Andreja
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Vodopija, A. (2018). Prepoznavanje znakova korištenjem TensorFlow biblioteke (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:503066

Vodopija, Andreja. "Prepoznavanje znakova korištenjem TensorFlow biblioteke." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:503066

Vodopija, Andreja. "Prepoznavanje znakova korištenjem TensorFlow biblioteke." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:503066

Vodopija, A. (2018). 'Prepoznavanje znakova korištenjem TensorFlow biblioteke', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 05 July 2024, https://urn.nsk.hr/urn:nbn:hr:168:503066

Vodopija A. Prepoznavanje znakova korištenjem TensorFlow biblioteke [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 July 05] Available at: https://urn.nsk.hr/urn:nbn:hr:168:503066

A. Vodopija, "Prepoznavanje znakova korištenjem TensorFlow biblioteke", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:503066

Metadata
TitlePrepoznavanje znakova korištenjem TensorFlow biblioteke
Title (english)Character Recognition Using TensorFlow Library
AuthorAndreja Vodopija
MentorTomislav Pribanić (mentor)
Committee memberTomislav Pribanić (predsjednik povjerenstva)
Committee memberTomislav Petković (član povjerenstva)
Committee memberMatea Đonlić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-09-19, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Postoje 3 vrste strojnog učenja: nadzirano, nenadzirano i podržano učenje. U ovom radu su opisane 3 metode nadziranog učenja: logistička regresija, softmax regresija i umjetne neuronske mreže. Logistička regresija služi za binarnu klasifikaciju, dok softmax regresija služi za višeklasnu klasifikaciju. S obzirom da ne daju dobre rezultate za linearno neodvojive probleme, takvi problemi se mogu rješavati umjetnim neuronskim mrežama zahvaljujući njenim skrivenim slojevima. Optičko prepoznavanje znakova implementirano je umjetnom neuronskom mrežom te se pri tome korisi biblotekom TensorFlow i podatcima iz baze MNIST. Veliku ulogu u treniranju umjetne neuronske mreže imaju takozvani hiperparametri: stopa učenja, veličina uzorka i broj epoha. Rezultati točnosti uvelike ovise o hiperparametrima mreže.
Abstract (english)
There are 3 types of machine learning: supervised, unsupervised and reinforcement learning. In this thesis are explained 3 methods of supervised learning: logistic regression, softmax regression and artificial neural networks. Logistic regression is used for binary classification while softmax is used for multiclass classification. These methods don't offer good results for linearly unseparable problems where artificial neural networks can be used thanks to their hidden-layers. Optical character recognition is implemented with neural networks and uses TensorFlow library and MNIST database. Hyperparameters play huge role in training and accuracy of a neural networks. Parameters that have been studied in this thesis are learning rate, batch size and number of epochs.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:503066
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 on2019-03-14 02:01:32