Distance Measures for HyperGP with Fitness Sharing
Identifikátory výsledku
Kód výsledku v IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00195563" target="_blank" >RIV/68407700:21230/12:00195563 - isvavai.cz</a>
Výsledek na webu
<a href="http://dl.acm.org/citation.cfm?id=2330241" target="_blank" >http://dl.acm.org/citation.cfm?id=2330241</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1145/2330163.2330241" target="_blank" >10.1145/2330163.2330241</a>
Alternativní jazyky
Jazyk výsledku
angličtina
Název v původním jazyce
Distance Measures for HyperGP with Fitness Sharing
Popis výsledku v původním jazyce
In this paper we propose a new algorithm called HyperGPEFS (HyperGP with Explicit Fitness Sharing). It is based on a HyperNEAT, which is a well-established evolutionary method employing indirect encoding of artificial neural networks. Indirect encoding in HyperNEAT is realized via special function called Compositional and Pattern Producing Network (CPPN), able to describe a neural network of arbitrary size. CPPNs are represented by network structures, which are evolved by means of a slightly modified version of another, well-known algorithm NEAT (NeuroEvolution of Augmenting Topologies). HyperGP is a variant of HyperNEAT, where the CPPNs are optimized by Genetic Programming (GP). Published results reported promising improvement in the speed of convergence. Our approach further extends HyperGP by using fitness sharing to promote a diversity of a population. Here, we thoroughly compare all three algorithms on six different tasks. Fitness sharing demands a definition of a tree distance me
Název v anglickém jazyce
Distance Measures for HyperGP with Fitness Sharing
Popis výsledku anglicky
In this paper we propose a new algorithm called HyperGPEFS (HyperGP with Explicit Fitness Sharing). It is based on a HyperNEAT, which is a well-established evolutionary method employing indirect encoding of artificial neural networks. Indirect encoding in HyperNEAT is realized via special function called Compositional and Pattern Producing Network (CPPN), able to describe a neural network of arbitrary size. CPPNs are represented by network structures, which are evolved by means of a slightly modified version of another, well-known algorithm NEAT (NeuroEvolution of Augmenting Topologies). HyperGP is a variant of HyperNEAT, where the CPPNs are optimized by Genetic Programming (GP). Published results reported promising improvement in the speed of convergence. Our approach further extends HyperGP by using fitness sharing to promote a diversity of a population. Here, we thoroughly compare all three algorithms on six different tasks. Fitness sharing demands a definition of a tree distance me
Klasifikace
Druh
D - Stať ve sborníku
CEP obor
IN - Informatika
OECD FORD obor
—
Návaznosti výsledku
Projekt
—
Návaznosti
I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace
Ostatní
Rok uplatnění
2012
Kód důvěrnosti údajů
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Údaje specifické pro druh výsledku
Název statě ve sborníku
Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion
ISBN
978-1-4503-1177-9
ISSN
—
e-ISSN
—
Počet stran výsledku
8
Strana od-do
545-552
Název nakladatele
ACM
Místo vydání
New York
Místo konání akce
Philadelphia
Datum konání akce
7. 7. 2012
Typ akce podle státní příslušnosti
WRD - Celosvětová akce
Kód UT WoS článku
000309611100069