Publication detail

Training a neural Network for a New Node element design

ŠKORPIL, V. PŘECECHTĚL, R.

Original Title

Training a neural Network for a New Node element design

English Title

Training a neural Network for a New Node element design

Type

journal article - other

Language

Czech

Original Abstract

This paper describes training a neural network for a new node element design. Neural networks are used to control network nodes instead of the control by sequential circuits. This article primarily discusses the management of routers. Routers are generally able to use all available topologies of a network. Simulation in MATLAB-SIMULINK has tested how the training networks route the given packets. It has been shown that Artificial Neural Networks (ANN) are suitable for the described aim.

English abstract

This paper describes training a neural network for a new node element design. Neural networks are used to control network nodes instead of the control by sequential circuits. This article primarily discusses the management of routers. Routers are generally able to use all available topologies of a network. Simulation in MATLAB-SIMULINK has tested how the training networks route the given packets. It has been shown that Artificial Neural Networks (ANN) are suitable for the described aim.

Keywords

Artificial Neural Network; Network Node; MATLAB –SIMULINK; Routing

Key words in English

Artificial Neural Network; Network Node; MATLAB –SIMULINK; Routing

Authors

ŠKORPIL, V.; PŘECECHTĚL, R.

RIV year

2013

Released

12. 2. 2013

ISBN

0033-2097

Periodical

Przeglad Elektrotechniczny

Year of study

2013

Number

2b

State

Republic of Poland

Pages from

187

Pages to

192

Pages count

5

BibTex

@article{BUT96854,
  author="Vladislav {Škorpil} and Roman {Přecechtěl}",
  title="Training a neural Network for a New Node element design",
  journal="Przeglad Elektrotechniczny",
  year="2013",
  volume="2013",
  number="2b",
  pages="187--192",
  issn="0033-2097"
}