prikaz prve stranice dokumenta Predviđanje vremenskih serija primjenom umjetnih neuronskih mreža
  Download
PDF 2.05 MB
undergraduate thesis
Predviđanje vremenskih serija primjenom umjetnih neuronskih mreža
2020. urn:nbn:hr:235:457762
Kukurin, Luka
University of Zagreb
Faculty of Mechanical Engineering and Naval Architecture

Cite this document

Kukurin, L. (2020). Predviđanje vremenskih serija primjenom umjetnih neuronskih mreža (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture. Retrieved from https://urn.nsk.hr/urn:nbn:hr:235:457762

Kukurin, Luka. "Predviđanje vremenskih serija primjenom umjetnih neuronskih mreža." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2020. https://urn.nsk.hr/urn:nbn:hr:235:457762

Kukurin, Luka. "Predviđanje vremenskih serija primjenom umjetnih neuronskih mreža." Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, 2020. https://urn.nsk.hr/urn:nbn:hr:235:457762

Kukurin, L. (2020). 'Predviđanje vremenskih serija primjenom umjetnih neuronskih mreža', Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, accessed 19 April 2024, https://urn.nsk.hr/urn:nbn:hr:235:457762

Kukurin L. Predviđanje vremenskih serija primjenom umjetnih neuronskih mreža [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture; 2020 [cited 2024 April 19] Available at: https://urn.nsk.hr/urn:nbn:hr:235:457762

L. Kukurin, "Predviđanje vremenskih serija primjenom umjetnih neuronskih mreža", Undergraduate thesis, University of Zagreb, Faculty of Mechanical Engineering and Naval Architecture, Zagreb, 2020. Available at: https://urn.nsk.hr/urn:nbn:hr:235:457762

Please login to the repository to save this object to your list.
Metadata
TitlePredviđanje vremenskih serija primjenom umjetnih neuronskih mreža
Title (english)Time series forecasting using artificial neural networks
AuthorLuka Kukurin
MentorDanko Brezak (mentor)
GranterUniversity of Zagreb
Faculty of Mechanical Engineering and Naval Architecture
Zagreb
Defense date and country2020-09-24, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Mechanical Engineering
Abstract
Neuronske mreže moćan su statistički alat, utoliko da ih je možda i pogrešno tako nazvati. Pokazuju svoj puni sjaj tamo gdje tradicionalne metode statistike nailaze na zapreke. Jedan takav primjer su kaotični sustavi. U ovom radu istražujemo koliko dobro neuronske mreže mogu predvidjeti Glass-Mackey kaotični sustav koristeći dva modela neuronskih mreža – statičku i dinamičku neuronsku mrežu, te uspoređujemo njihove rezultate.
Abstract (english)
Neural networks are a powerful statistical tool, so much that it might be wrong to call them a statistical tool. They shine where traditional statistics hit a brick wall. One of such cases are chaotic systems. In this paper we investigate how well can neural networks predict the Glass-Mackey equation using two different models of nerual networks – a static neural network and a dynamic neural network, and we compare their results.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:235:457762
Study programmeTitle: Mechanical Engineering
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka strojarstva)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2020-09-17 15:35:38