NEAT in HyperNEAT Substituted with Genetic Programming

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F09%3A00159310" target="_blank" >RIV/68407700:21230/09:00159310 - isvavai.cz</a>

Result on the web

—

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

NEAT in HyperNEAT Substituted with Genetic Programming

Original language description

In this paper we present application of genetic programming (GP) to evolution of indirect encoding of neural network weights. We compare usage of original HyperNEAT algorithm with our implementation, in which we replaced the underlying NEAT with geneticprogramming. The algorithm was named HyperGP. The evolved neural networks were used as controllers of autonomous mobile agents (robots) in simulation. The agents were trained to drive with maximum average speed. This forces them to learn how to drive onroads and avoid collisions. The genetic programming lacking the NEAT complexification property shows better exploration ability and tends to generate more complex solutions in fewer generations. On the other hand, the basic genetic programming generatesquite complex functions for weights generation. Both approaches generate neural controllers with similar abilities.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

IN - Informatics

OECD FORD branch

—

Project

—

Continuities

Z - Vyzkumny zamer (s odkazem do CEZ)

Publication year

2009

Confidentiality

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

Article name in the collection

Adaptive and Natural Computing Algorithms

ISBN

978-3-642-04920-0

ISSN

0302-9743

e-ISSN

—

Number of pages

10

Pages from-to

—

Publisher name

Springer

Place of publication

Heidelberg

Event location

Kuopio

Event date

Apr 23, 2009

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—