20.500.12556/DKUM-78125 Klasifikacija z utežem agnostičnimi nevronskimi mrežami magistrsko delo Classification with weight agnostic neural networks V magistrskem delu je predstavljena metoda iskanja utežem agnostičnih nevronskih mrež, ki temelji na genetskem algoritmu, imenovanem NeuroEvolution of Augmenting Topologies (NEAT). Evalviranje genomov z vzorčenjem uteži iz fiksne uniformne množice naključnih vrednosti minimizira pomembnost uteži, s čimer je poudarek le na optimizaciji topologije. To omogoča utežem agnostičnim nevronskim mrežam opravljanje različnih nalog brez predhodnega učenja utežnih vrednosti. Naša implementacija je bila prilagojena za povezovanje z odprtokodno knjižnico Scikit-learn, ki smo jo javno objavili v obliki PyPi paketa. V eksperimentalnem delu smo se osredotočili na primerjavo evolucijskih in utežem agnostičnih nevronskih mrež na primeru reševanja klasifikacijskih problemov. Rezultate smo evalvirali z uporabo statističnih metod, ki so pokazale, da utežem agnostične nevronske mreže proizvedejo več skritih nevronov kot evolucijske, vendar uspejo doseči primerljivo točnost zgolj s pravilno topologijo, brez optimizacije uteži. In our master's thesis, we reviewed a search method for weight agnostic neural networks that are based on a genetic algorithm called NeuroEvolution of Augmenting Topologies (NEAT). Evaluating genomes by sampling weights from a fixed uniform random distribution ensures the importance of weights is minimized and the main focus is on optimizing the topology. This gives weight agnostic neural networks an ability to solve different tasks without explicit weight training. Our implementation was made to be compatible with an open-source library called Scikit-learn, and we published it as a public PyPi package. In our experiments, we focused on comparing evolutionary neural networks with weight agnostic neural networks by solving different classification tasks. We evaluated the results with the use of statistical methods which showed that while weight agnostic neural networks created more hidden nodes, their topologies were able to achieve comparable accuracy without optimizing the weights. utežem agnostične nevronske mreže klasifikacija nevroevolucija NEAT weight agnostic neural networks classification neuroevolution NEAT true true false [M. Mlakar] Slovenski jezik Angleški jezik Magistrsko delo/naloga 2020-10-29 20:30:34 2020-12-01 13:29:39 2022-08-09 17:36:37 2021-01-06 03:22:13 2020 0 Maribor 0 Maribor XI, 73 f. 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.8(043.2) 45029891 URN:SI:UM:DK:90QBCR3J MAG_Mlakar_Marko_2020.pdf MAG_Mlakar_Marko_2020.pdf 1 034D29583016FD8F4080A5A7DC88109B 52530a993c372bced6a194efdd75709fc19632df6e2f039aa431252c32b0dcb1 fb1a3566-7c11-11eb-bb7a-00155d0001ca 20.500.12556/dkum/25bfbf22-0743-422a-9440-fb7f8031157e https://dk.um.si/Dokument.php?lang=slv&id=147299 Fakulteta za elektrotehniko, računalništvo in informatiko 0 0 0