Sustav za semantičku segmentaciju primjenom dubokog učenja

undergraduate thesis

• Title (english): System for Semantic Segmentation Using Deep Learning
• Author: Zvonimir Vujnović
• Mentor: Tomislav Hrkać (mentor)
• Committee member: Tomislav Hrkać (predsjednik povjerenstva)
• Committee member: Marin Oršić (član povjerenstva)
• Committee member: Josip Šarić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-12, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom su radu opisane umjetne neuronske mreže. Sve od toga kako su građene, kako svaki njihov neuron obrađuje informacije te kako to rade kao cjelina i uče po primjerima. Cilj je dubokog učenja da model mreže počinje učiti kao i čovjek, po vlastitom iskustvu. Semantička segmentacija samo je dio spektra u kojemu se primjenjuje duboko učenje. Semantička segmentacija je ujedno i veoma popularno područje računalnog vida jer pridonosi na putu prema savršenom razumijevanju slike što je danas veoma korišten dio umjetne inteligencije.

Abstract (english)

This paper describes artificial neural networks. Everything from how they are built, how each and every neuron in the network processes information and how all of the neurons do it as a whole to learn from examples. The goal of deep learning is to make a model that can learn as efficiently as a human, from its experience. Semantic Segmentation is only a part of spectrum in which deep learning is applied. Semantic Segmentation is also very popular area of computer vision because it contributes to the perfect understanding of a picture which is now widely used in artificial intelligence.

• Keywords: umjetna neuronska mreža; neuron; duboko učenje; umjetna inteligencija; računalni vid; semantička segmentacija
• Keywords (english): artificial neural network; neuron; deep learning; artificial intelligence; computer vision; semantic segmentation
• Language: croatian
• URN:NBN: urn:nbn:hr:168:584203
• Study programme: Title: 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 resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2020-01-07 23:01:44