prikaz prve stranice dokumenta Dubinsko učenje s primjenom u klasifikaciji uzoraka
  Download
PDF 157.42 KB
undergraduate thesis
Dubinsko učenje s primjenom u klasifikaciji uzoraka
2015. urn:nbn:hr:200:081141
Bakula, Bruno
Josip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
Department of Software Engineering
Chair of Programming Languages and Systems

Cite this document

Bakula, B. (2015). Dubinsko učenje s primjenom u klasifikaciji uzoraka (Undergraduate thesis). Retrieved from https://urn.nsk.hr/urn:nbn:hr:200:081141

Bakula, Bruno. "Dubinsko učenje s primjenom u klasifikaciji uzoraka." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2015. https://urn.nsk.hr/urn:nbn:hr:200:081141

Bakula, Bruno. "Dubinsko učenje s primjenom u klasifikaciji uzoraka." Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, 2015. https://urn.nsk.hr/urn:nbn:hr:200:081141

Bakula, B. (2015). 'Dubinsko učenje s primjenom u klasifikaciji uzoraka', Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, accessed 29 July 2021, https://urn.nsk.hr/urn:nbn:hr:200:081141

Bakula B. Dubinsko učenje s primjenom u klasifikaciji uzoraka [Undergraduate thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek; 2015 [cited 2021 July 29] Available at: https://urn.nsk.hr/urn:nbn:hr:200:081141

B. Bakula, "Dubinsko učenje s primjenom u klasifikaciji uzoraka", Undergraduate thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Electrical Engineering, Computer Science and Information Technology Osijek, Osijek, 2015. Available at: https://urn.nsk.hr/urn:nbn:hr:200:081141

Islandora Bookmark - Please login to use this feature
Metadata
TitleDubinsko učenje s primjenom u klasifikaciji uzoraka
Title (english)Deep Learning with application in pattern classification
AuthorBruno Bakula
MentorGoran Martinović (mentor)
MentorBruno Zorić (mentor)
Committee memberGoran Martinović (član povjerenstva)
Committee memberHrvoje Glavaš (član povjerenstva)
Committee memberKrešimir Nenadić (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Electrical Engineering, Computer Science and Information Technology Osijek
(Department of Software Engineering)
(Chair of Programming Languages and Systems)
Osijek
Defense date and country2015-07-09, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Program Engineering
Abstract
U ovome radu objašnjen je koncept dubinskog učenja, kao naprednog postupka učenja različitih razina značajki podataka. Arhitektura dubinskih neuronskih mreža mnogo je složenija od arhitekture standardnih mreža, te sadrži minimalno dva skrivena sloja. Tri glavne arhitekture dubinskih mreža su naslagani autoenkoderi, deep belief networks i konvolucijske mreže. Naslagani autoenkoderi grade se od prethodno treniranih, običnih autoenkodera. Nakon postupka predtreniranja, cijela mreža se fino podešava čime je postupak treniranja završen. Traje višestruko duže u odnosu na treniranje standardnih mreže. Na provedenim eksperimentima ostvaren je značajan napredak u točnosti klasifikacije korištenjem naslaganih autoenkodera, u odnosu na standardne neuronske mreže. Potrebno je eksperimentirati sa različitim dimenzijama skrivenih slojeva, kako bi se pronašle optimalne postavke rada dubinskih mreža, za određeni skup podataka. Ključne riječi: autoenkoder, dubinsko učenje, naslagani autoenkoderi, neuronske mreže, pohlepno treniranje po slojevima
Abstract (english)
n this paper, the concept of deep learning as an advanced method for learning different levels of data features, was explained. Deep neural networks architecture is far more complex compared to standard network architectures, and it consists of minimum two hidden layers. Three main deep network architectures are stacked autoencoders, deep belief networks and convolutional networks. Stacked autoencoders are composed of normal autoencoders that were previously trained. After the pretraining step, the whole network is fine tuned, which finishes the training process. The training process duration is multiplied, regarding to standard networks training. A significant improvement in clasiffication accuracy was made in experiments using stacked autoencoders, in contrary to standard neural networks. Experimenting with different dimension of hidden layers is needed to find optimal settings for running deep networks, applied on specific data set.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:200:081141
Study programmeTitle: Undergraduate University Study Programme in Computer Engineering
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 conditionsOpen access
Terms of useLicence In copyright icon
Created on2016-05-06 11:06:23