On the Evolutionary Neural Network Creation Using Native Visibility Graph

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27240%2F19%3A10244014" target="_blank" >RIV/61989100:27240/19:10244014 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/abstract/document/8789941" target="_blank" >https://ieeexplore.ieee.org/abstract/document/8789941</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/CEC.2019.8789941" target="_blank" >10.1109/CEC.2019.8789941</a>

Jazyk výsledku

angličtina

Název v původním jazyce

On the Evolutionary Neural Network Creation Using Native Visibility Graph

Popis výsledku v původním jazyce

In this article, a novel way of creating the feed forward neural network is presented. This model is inspired by native visibility graph, and the networks are created by well-known differential evolution algorithm. In the experiment parts, we compared these networks with multi-layer perceptron. We have found that our novel approach creates smaller networks comparing to multi-layer perceptron and also, the decision space differs. The decision space was similar for multi-layer perceptron for almost all training runs from 51 repetitions, but for our novel approach, the decision space differs and also creates more complex patterns.

Název v anglickém jazyce

On the Evolutionary Neural Network Creation Using Native Visibility Graph

Popis výsledku anglicky

In this article, a novel way of creating the feed forward neural network is presented. This model is inspired by native visibility graph, and the networks are created by well-known differential evolution algorithm. In the experiment parts, we compared these networks with multi-layer perceptron. We have found that our novel approach creates smaller networks comparing to multi-layer perceptron and also, the decision space differs. The decision space was similar for multi-layer perceptron for almost all training runs from 51 repetitions, but for our novel approach, the decision space differs and also creates more complex patterns.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10200 - Computer and information sciences

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2019 IEEE Congress on Evolutionary Computation, CEC 2019 - Proceedings

ISBN

978-1-72812-153-6

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

1494-1501

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Wellington

Datum konání akce

10. 6. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000502087101069