Klasifikacija uporabom umjetnih neuronskih mreža

undergraduate thesis

• Title (english): Classification Based on Artificial Neural Networks
• Author: Darijo Brčina
• Mentor: Marko Čupić (mentor)
• Committee member: Marko Čupić (predsjednik povjerenstva)
• Committee member: Rudolf Lovrenčić (član povjerenstva)
• Committee member: Karlo Knežević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Raspoznavanje uzoraka te klasifikacija istih je jedan od bitnijih problema računarske znanosti. Najveći izazov je konstruirati kvalitetan klasifikator koji je sposoban generalizirati. U ovom radu prikazan je teorijski pogled na algoritam umjetne neuronske mreže kroz povijest pa do danas i njegovo učenje backpropagation algoritmom. Također, uz rad je i implementirano jedno takvo učenje kroz grafičko korisničko sučelje kroz koje korisnik interaktivno unosi točke iz 2D koordinatnog sustava labelirane različitim razredima i prati koliko kvalitetno klasifikator uči. Reprezentativni rezultati prikazani su i dokumentirani u radu.

Abstract (english)

Pattern recognition and classification is one of the most important problem in computer science. The biggest challenge is to construct a good classifier that is capable of generalizing. This paper presents a theoretical view of the artificial neural network algorithm through history to the present day and its learning by the backpropagation algorithm. Also, in addition to the work, one such learning was implemented through a graphical user interface through which the user interactively enters points from the 2D coordinate system labeled with different classes and monitors how well the classifier learns. Representative results are presented and documented in the paper.

• Keywords: nadzirano učenje; klasifikacija; unaprijedna neuronska mreža; algoritam propagacije pogreške unatrag; aktivacijska funkcija; umjetni neuron
• Keywords (english): supervised learning; classification; feedforward neural network; backpropagation; activation function; artificial neuron
• Language: croatian
• URN:NBN: urn:nbn:hr:168:809350
• 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: 2023-01-14 08:35:24