prikaz prve stranice dokumenta Custom Vision i LUIS servisi na Microsoft Azureu
  Download
PDF 1.3 MB
master's thesis
Custom Vision i LUIS servisi na Microsoft Azureu
2018. urn:nbn:hr:126:394701
Markovinović, Eugen
Josip Juraj Strossmayer University of Osijek
Department of Mathematics
Chair of Applied Mathematics
Computer Science Research Group

Cite this document

Markovinović, E. (2018). Custom Vision i LUIS servisi na Microsoft Azureu (Master's thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:126:394701

Markovinović, Eugen. "Custom Vision i LUIS servisi na Microsoft Azureu." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2018. https://urn.nsk.hr/urn:nbn:hr:126:394701

Markovinović, Eugen. "Custom Vision i LUIS servisi na Microsoft Azureu." Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, 2018. https://urn.nsk.hr/urn:nbn:hr:126:394701

Markovinović, E. (2018). 'Custom Vision i LUIS servisi na Microsoft Azureu', Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, accessed 27 September 2020, https://urn.nsk.hr/urn:nbn:hr:126:394701

Markovinović E. Custom Vision i LUIS servisi na Microsoft Azureu [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Department of Mathematics; 2018 [cited 2020 September 27] Available at: https://urn.nsk.hr/urn:nbn:hr:126:394701

E. Markovinović, "Custom Vision i LUIS servisi na Microsoft Azureu", Master's thesis, Josip Juraj Strossmayer University of Osijek, Department of Mathematics, Osijek, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:126:394701

Islandora Bookmark - Please login to use this feature
Metadata
TitleCustom Vision i LUIS servisi na Microsoft Azureu
Title (english)Custom Vision and LUIS Services on Microsoft Azure
AuthorEugen Markovinović
MentorDomagoj Matijević (mentor)
Committee memberDomagoj Ševerdija (predsjednik povjerenstva)
Committee memberDomagoj Matijević (član povjerenstva)
Committee memberSlobodan Jelić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Department of Mathematics
(Chair of Applied Mathematics)
(Computer Science Research Group)
Osijek
Defense date and country2018-11-06, Croatia
Scientific / art field,
discipline and subdiscipline		NATURAL SCIENCES
Mathematics
Abstract
Ovaj diplomski rad za temu ima prikaz i implementaciju Microsoft-ovih servisa Custom Vision i LUIS. Prvo je ukratko opisan koncept strojnoga učenja i objašnjeni osnovni pojmovi kao regresija, klasifikacija, komponente učenja. Pojašnjen je i pojam neuronskih mreža kao i učenje bez nadzora. Praktični dio ovoga seminara je obuhvatio izradu jednostavnoga bota koji koristi LUIS i Custom Vision servise. U radu je objašnjeno kako koristiti LUIS i Custom Vision. Nadalje, objašnjena je izrada slika konveksnih mnogokuta u matlabu koje su služile za trening Custom Vision servisa. Konačno, opisana je izrada bota, u kojoj je obuhvaćeno korištenje bot framework-a. Ukratko je opisano kako bot framework radi i neke njegove značajke. Pokazan je način spajanja iz Visual Studia sa Azure servisima. Te konačno kao produkt praktičnoga dijela je dan funkcionalni bot koji može prepoznavati konveksne mnogokute.
Abstract (english)
This final thesis is about the display and implementation of Microsoft services Custom Vision and LUIS. To begin with, the concept of machine learning and the basic terms like regression, classification, features are explained. The concept of neural networks has also been explained as well as unsupervised learning. The practical part of this thesis involved developing a simple bot that uses LUIS and Custom Vision services. In the thesis it has been explained how to use LUIS and Custom Vision. Furthermore, the process of making images of convex polygons in matlab, that were used to train Custom Vision service has been explained. Finally, the making of the bot has been explained, the explanation involved using the bot framework. Briefly it has been discussed how bot framework works and some of it's features. It has been shown how to connect from Visual Studio to the Azure services. Finally, as the product of the practical part, a functional bot has been made that is able to recognise convex polygons.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:126:394701
Study programmeTitle: Mathematics; specializations in: Financial and Statistical Mathematics, Mathematics and Computer Science, Industrial and Applied Mathematics
Course: Mathematics and Computer Science
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2018-11-20 08:10:35