prikaz prve stranice dokumenta Uvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže
Access restricted to students and staff of home institution
undergraduate thesis
Uvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže
Split: University of Split, University of Split, Faculty of science, 2017. urn:nbn:hr:166:727029
Bratić, Tea
University of Split
Faculty of Science
Department of Informatics

Cite this document

Bratić, T. (2017). Uvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže (Undergraduate thesis). Split: University of Split, Faculty of Science. Retrieved from https://urn.nsk.hr/urn:nbn:hr:166:727029

Bratić, Tea. "Uvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže." Undergraduate thesis, University of Split, Faculty of Science, 2017. https://urn.nsk.hr/urn:nbn:hr:166:727029

Bratić, Tea. "Uvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže." Undergraduate thesis, University of Split, Faculty of Science, 2017. https://urn.nsk.hr/urn:nbn:hr:166:727029

Bratić, T. (2017). 'Uvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže', Undergraduate thesis, University of Split, Faculty of Science, accessed 19 April 2024, https://urn.nsk.hr/urn:nbn:hr:166:727029

Bratić T. Uvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže [Undergraduate thesis]. Split: University of Split, Faculty of Science; 2017 [cited 2024 April 19] Available at: https://urn.nsk.hr/urn:nbn:hr:166:727029

T. Bratić, "Uvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže", Undergraduate thesis, University of Split, Faculty of Science, Split, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:166:727029

Please login to the repository to save this object to your list.
Metadata
TitleUvježbavanje ponašanja fizičkog agenta uporabom neuronske mreže
Title (english)Behavior training of physical agents using neural networks
AuthorTea Bratić
MentorSaša Mladenović (mentor)
Committee memberSaša Mladenović (predsjednik povjerenstva)
Committee memberGoran Zaharija (član povjerenstva)
Committee memberDivna Krpan (član povjerenstva)
GranterUniversity of Split
Faculty of Science
(Department of Informatics)
Split
Defense date and country2017-09-15, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
U ovom radu je prikazan program u kojem se nalazi neuronska mreža i kod za upravljanje robotom. Uz pomoć algoritma povratne propagacije konstruiramo neuronsku mrežu. Pokušavamo eksperimentalnim putem odrediti optimalni broj neurona u skrivenom sloju i broj potrebnih epoha, jer ne postoji jedinstvena formula za određivanje tih parametara. Ako je broj epoha prevelik, doći će do pretreniranosti mreže, a ako je premalen, mreža se neće uspjeti istrenirati. Ulazni set podataka za treniranje mreže je osmišljen da robot koji simbolizira psa ima logične izlaze s obzirom na ulaze, tako na primjer, ako pas vidi crvenu boju i rep mu se dira akcija psa će biti lajanje. Kad smo mrežu istrenirali, primjenjujemo je na psu koji predstavlja fizički dio agenta. Ulazi će se očitavati sa senzora, a akcije dobivamo pomoću motora i zvuka koji se nalaze na robotu.
Abstract (english)
This thesis describes the creation and implementation of a program which includes a neural network and the code to control a physical agent – a robot dog. A neural network is created by using the backpropagation algorithm. Since a unique mathematical expression to determine the optimal number of hidden layer neurons and the required number of epochs doesn't exist, the experimental part of the paper focuses on determining those parameters. If the number of epochs is too large, the network will become overtrained and in the case of selecting a too small number of epochs, the network will be unable to train itself. The input set of data required to train the network is designed in such a way that a robot, representing a dog, has logical outputs in regard to the inputs. For example, if the dog percieves the color red and its tail is touched, it will respond with barking. Once the training is complete, the trained network is applied to the dog, which represents the physical part of the agent. The input data is fed through the dog's sensors and the actions are performed by it's built in motors and sounds.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:166:727029
Study programmeTitle: Computer Science
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike (sveučilišni/a prvostupnik/prvostupnica (baccalaureus/baccalaurea) informatike)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
RepositoryRepository of Faculty of Science
Created on2018-04-27 16:10:39