Klasifikacija slika kućnih brojeva dubokim konvolucijskim modelima

undergraduate thesis

• Title (english): Classification of Street-View House Numbers With Deep Convolutional Models
• Author: Ivan Šego
• Mentor: Siniša Šegvić (mentor)
• Committee member: Siniša Šegvić (predsjednik povjerenstva)
• Committee member: Marin Oršić (član povjerenstva)
• Committee member: Ivan Krešo (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2018-09-13, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Rad započinje opisom općenito neuronskih mreža, neurona te njihove inspiracije. Nas-
tavlja se opisom konvolucijskih neuronskih mreža te njihove primjene na klasifika-
ciju objekta. U nastavku je dan pregled programskog okvira PyTorch. Nadalje, dani
je prikaz rezultat implementirane konvolucijske neuronske mreža skupovima SVHN,
MNIST te njihova programska implementacija. Dodatno, objašnjen je koncept nepri-
jateljskih primjera te prikazan jedan konkretan neprijateljski primjer

Abstract (english)

This works starts with a general description of artificial neural networks, neurons and
their inspiration. It continues with a description of convolutional neural network and
their application to a classification of objects. Then, it is given an overview of library
PyTroch. Then, it is given an overview of the results implementing convolutional
neural network on datasets SVHN, MNIST and their code in PyTorch. Additionally,
concept of adversarial examples is shown and one concrete adversarial... More examples is
given. Less

• Keywords: Umjetne neuronske mreže; duboke neuronske mreže; konvolucijske neuronske mreže; duboko učenje; strojno učenje; klasifikacija; kućni brojevi; SVHN
• Keywords (english): Artifical neural networks; deep neural networks; convolutional neural networks; deep learning; machine learning; classification; house numbers; SVHN
• Language: croatian
• URN:NBN: urn:nbn:hr:168:671588
• 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: 2019-03-14 01:11:03