Influence of the structure on the possibilities of neural networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F46747885%3A24210%2F15%3A00002791" target="_blank" >RIV/46747885:24210/15:00002791 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Influence of the structure on the possibilities of neural networks

Popis výsledku v původním jazyce

The article briefly describes the possibilities and usage of neural networks. It further deals with the McCulloch-Pitts neuron artificial model. The article also focuses on the analysis of the architecture of neural networks with regard on the possibility of application. Among the described architectures there are preceptron, layered neural networks and long short term memory architecture. Further attention is paid to the issue of layered neural networks architecture and to the increase of computing demands in relation to the number of neurons in the hidden layers. The second monitored parameter is the number of hidden layers and its influence on the computing time of the neural network. The conclusion provides the measurements results of the computingtime speed of neural networks and evaluation of the achieved results.

Název v anglickém jazyce

Influence of the structure on the possibilities of neural networks

Popis výsledku anglicky

The article briefly describes the possibilities and usage of neural networks. It further deals with the McCulloch-Pitts neuron artificial model. The article also focuses on the analysis of the architecture of neural networks with regard on the possibility of application. Among the described architectures there are preceptron, layered neural networks and long short term memory architecture. Further attention is paid to the issue of layered neural networks architecture and to the increase of computing demands in relation to the number of neurons in the hidden layers. The second monitored parameter is the number of hidden layers and its influence on the computing time of the neural network. The conclusion provides the measurements results of the computingtime speed of neural networks and evaluation of the achieved results.

Druh

O - Ostatní výsledky

CEP obor

JB - Senzory, čidla, měření a regulace

OECD FORD obor

—

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2015

Kód důvěrnosti údajů

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