Towards Evolutionary Design of Complex Systems Inspired by Nature

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F14%3A00224724" target="_blank" >RIV/68407700:21230/14:00224724 - isvavai.cz</a>

Výsledek na webu

<a href="https://ojs.cvut.cz/ojs/index.php/ap/article/view/AP.2014.54.0367" target="_blank" >https://ojs.cvut.cz/ojs/index.php/ap/article/view/AP.2014.54.0367</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.14311/AP.2014.54.0367" target="_blank" >10.14311/AP.2014.54.0367</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Towards Evolutionary Design of Complex Systems Inspired by Nature

Popis výsledku v původním jazyce

This paper presents first steps towards evolutionary design of complex autonomous systems. The approach is inspired by modularity of human brain and principles of evolution. Rather than evolving neural networks or neural-based systems, the approach focuses on evolving hybrid networks composed of heterogeneous sub-systems implementing various algorithms/behaviors. Currently, the evolutionary techniques are used to optimize weights between predefined blocks (so called Neural Modules) in order to find an agent architecture appropriate for given task. The framework, together with the simulator of such systems is presented. Then, examples of agent architectures represented as hybrid networks are presented. One architecture is hand-designed and one is automatically optimized by means of Evolutionary Algorithm. Even on such a simple experiment, it can be observed how the evolution is able to pick-up unexpected attributes of the task and exploit them when designing new architecture.

Název v anglickém jazyce

Towards Evolutionary Design of Complex Systems Inspired by Nature

Popis výsledku anglicky

This paper presents first steps towards evolutionary design of complex autonomous systems. The approach is inspired by modularity of human brain and principles of evolution. Rather than evolving neural networks or neural-based systems, the approach focuses on evolving hybrid networks composed of heterogeneous sub-systems implementing various algorithms/behaviors. Currently, the evolutionary techniques are used to optimize weights between predefined blocks (so called Neural Modules) in order to find an agent architecture appropriate for given task. The framework, together with the simulator of such systems is presented. Then, examples of agent architectures represented as hybrid networks are presented. One architecture is hand-designed and one is automatically optimized by means of Evolutionary Algorithm. Even on such a simple experiment, it can be observed how the evolution is able to pick-up unexpected attributes of the task and exploit them when designing new architecture.

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JC - Počítačový hardware a software

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2014

Kód důvěrnosti údajů

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

Název periodika

Acta Polytechnica

ISSN

1210-2709

e-ISSN

—

Svazek periodika

54

Číslo periodika v rámci svazku

5

Stát vydavatele periodika

CZ - Česká republika

Počet stran výsledku

11

Strana od-do

367-377

Kód UT WoS článku

—

EID výsledku v databázi Scopus

—