Publ3 search

Z6_60GI02O0O8IDC0QEJUJ26TJDI4

> Publ3 search

Error:

Javascript is disabled in this browser. This page requires Javascript. Modify your browser's settings to allow Javascript to execute. See your browser's documentation for specific instructions.

Publikační činnost

Probíhá načítání, čekejte prosím...

Typ záznamu:	stať ve sborníku (D)
Domácí pracoviště:	Katedra informatiky a počítačů (31400)
Název:	An emergence of modular connectionist architecture of neural network
Citace	Volná, E. An emergence of modular connectionist architecture of neural network. In: International conference on soft computing, MENDEL 2003: Proceedings of the ninth International conference on soft computing, MENDEL 2003 4.6.2003 Brno. Brno: VUT Brno, 2003. VUT Brno, 2003. s. 173-176. ISBN 80-214-2411-7.

Podnázev
Rok vydání:	2003
Obor:	Využití počítačů, robotika a její aplikace
Počet stran:
Strana od:	173
Strana do:	176
Forma vydání:
Kód ISBN:	80-214-2411-7
Kód ISSN:
Název sborníku:	Proceedings of the ninth International conference on soft computing, MENDEL 2003
Sborník:
Název nakladatele:	VUT Brno
Místo vydání:	Brno
Stát vydání:	Sborník vydaný v ČR
Název konference:	International conference on soft computing, MENDEL 2003
Místo konání konference:	Brno
Datum zahájení konference:
Typ akce podle státní příslušnosti účastníků:	Evropská akce
Kód UT WoS:
EID:

Klíčová slova anglicky:	Emergence; Probability vector; Modularity
Popis v původním jazyce:	This method is based on the article [1]. We used the probability vector that helps to construction of n ? bit vectors, e.g. individuals in the population. All individuals in every generation are randomly generated from the probability vector that is associated with this generation. The probability vector is updated on the basis of best individuals in a population in order that it was near upon a best solution with every next generation. The process is repeated until the probability vector entries are close to zero or to one. The resulting probability vector then determines an optimal solution of the given optimalization task. This method is based on principles of evolutionary algorithms and it builds a modular architecture of the neural network. The modular network for a given task emerges as a winning architecture obtained by interference between modules.
Popis v anglickém jazyce:	This method is based on the article [1]. We used the probability vector that helps to construction of n ? bit vectors, e.g. individuals in the population. All individuals in every generation are randomly generated from the probability vector that is associated with this generation. The probability vector is updated on the basis of best individuals in a population in order that it was near upon a best solution with every next generation. The process is repeated until the probability vector entries are close to zero or to one. The resulting probability vector then determines an optimal solution of the given optimalization task. This method is based on principles of evolutionary algorithms and it builds a modular architecture of the neural network. The modular network for a given task emerges as a winning architecture obtained by interference between modules.

Seznam ohlasů

Ohlas

R01:

Complementary Content

${loading}