| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:METODE NEVROEVOLUCIJE
Authors:ID Mađarić, Sašo (Author)
ID Strnad, Damjan (Mentor) More about this mentor... New window
ID Guid, Nikola (Comentor)
Files:.pdf MAG_Madaric_Saso_2013.pdf (5,83 MB)
MD5: FBC14D1BECD1B4862D4A06B0B4CCD23B
 
Language:Slovenian
Work type:Master's thesis/paper
Typology:2.09 - Master's Thesis
Organization:FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Pri klasičnem razvoju nevronskih mrež za uporabo na različnih področjih umetne inteligence se pogosto srečujemo s problemom določanja optimalne topologije nevronske mreže, ki ima velik vpliv na njeno kvaliteto. V tem magistrskem delu smo se ukvarjali s problemom avtomatiziranega razvoja topologije nevronske mreže in njenega učenja z nevroevolucijskimi metodami. Področje, ki se ukvarja z razvojem nevronskih mrež s pomočjo evolucijskega algoritma, je nevroevolucija. Preučili in implementirali smo nevroevolucijske metode NEAT, HyperNEAT in ES-HyperNEAT. Uspešnost metod smo preizkusili na eksperimentu z agenti. Agent se nahaja v okolju in poskuša pobrati čim več kosov hrane ter se izogniti sovražnikom oziroma zidovom. Nevroevolucijske metode smo primerjali z metodo Q-učenje, ki za učenje nevronske mreže uporablja klasično metodo vzvratnega prenosa napake. Primerjali smo doseženo oceno in časovno zahtevnost. Rezultati so pokazali, da je najuspešnejša metoda HyperNEAT, sledita pa ji ES-HyperNEAT in NEAT. Metoda Q-učenje se je izkazala za najmanj uspešno, saj je glede na nevroevolucijske metode v podrejenem položaju tako po doseženi kriterijski oceni kot tudi po časovni zahtevnosti.
Keywords:umetna inteligenca, nevroevolucija, evolucijski algoritem, nevronske mreže, razvoj nevronskih mrež, NEAT, HyperNEAT, ES-HyperNEAT
Place of publishing:Maribor
Publisher:[S. Mađarić]
Year of publishing:2013
PID:20.500.12556/DKUM-41489 New window
UDC:004.032.26:004.832.3(043.3)
COBISS.SI-ID:17335318 New window
NUK URN:URN:SI:UM:DK:1OF1WLB5
Publication date in DKUM:11.09.2013
Views:2514
Downloads:268
Metadata:XML DC-XML DC-RDF
Categories:KTFMB - FERI
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:NEUROEVOLUTION METHODS
Abstract:In classical development of neural networks for use in different areas of artificial intelligence we are often faced with the problem of optimal neural network topology selection, which has strong impact on neural network quality. In this master work we were studying with problem of automated development and training neural network topologies using neuroevolution methods. Development of NN topology using evolutionary algorithm is called nevroevolution. We have studied and implemented neuroevolution methods NEAT, HyperNEAT, and ES-HyperNEAT. The methods were compared using an experiment, where an agent tries to collect food and avoid enemies and walls. Neuroevolutionary methods were compared with the Q-learning, which uses backpropagation algorithm for neural network learning. The comparison was based on achieved fitness and time complexity. Results show, that the best method is HyperNEAT, followed by ES-HyperNEAT and NEAT. Method Q-learning method was least successful in both the achieved fitness and time complexity.
Keywords:artificial intelligence, nevroevolution, evolutionary algorithm, neural network, neural networks development, NEAT, HyperNEAT, ES-HyperNEAT


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica