Cargando…

Creative AI Through Evolutionary Computation: Principles and Examples

The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new. Such solutions exist in extremely large, high-dimensional, and complex search spaces. Population-based search techniques, i.e. variants of evolutionary computation, are well sui...

Descripción completa

Detalles Bibliográficos
Autor principal: Miikkulainen, Risto
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Springer Singapore 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7986182/
https://www.ncbi.nlm.nih.gov/pubmed/33778772
http://dx.doi.org/10.1007/s42979-021-00540-9
_version_ 1783668394200924160
author Miikkulainen, Risto
author_facet Miikkulainen, Risto
author_sort Miikkulainen, Risto
collection PubMed
description The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new. Such solutions exist in extremely large, high-dimensional, and complex search spaces. Population-based search techniques, i.e. variants of evolutionary computation, are well suited to finding them. These techniques make it possible to find creative solutions to practical problems in the real world, making creative AI through evolutionary computation the likely “next deep learning.”
format Online
Article
Text
id pubmed-7986182
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Springer Singapore
record_format MEDLINE/PubMed
spelling pubmed-79861822021-03-24 Creative AI Through Evolutionary Computation: Principles and Examples Miikkulainen, Risto SN Comput Sci Original Research The main power of artificial intelligence is not in modeling what we already know, but in creating solutions that are new. Such solutions exist in extremely large, high-dimensional, and complex search spaces. Population-based search techniques, i.e. variants of evolutionary computation, are well suited to finding them. These techniques make it possible to find creative solutions to practical problems in the real world, making creative AI through evolutionary computation the likely “next deep learning.” Springer Singapore 2021-03-23 2021 /pmc/articles/PMC7986182/ /pubmed/33778772 http://dx.doi.org/10.1007/s42979-021-00540-9 Text en © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. part of Springer Nature 2021 This article is made available via the PMC Open Access Subset for unrestricted research re-use and secondary analysis in any form or by any means with acknowledgement of the original source. These permissions are granted for the duration of the World Health Organization (WHO) declaration of COVID-19 as a global pandemic.
spellingShingle Original Research
Miikkulainen, Risto
Creative AI Through Evolutionary Computation: Principles and Examples
title Creative AI Through Evolutionary Computation: Principles and Examples
title_full Creative AI Through Evolutionary Computation: Principles and Examples
title_fullStr Creative AI Through Evolutionary Computation: Principles and Examples
title_full_unstemmed Creative AI Through Evolutionary Computation: Principles and Examples
title_short Creative AI Through Evolutionary Computation: Principles and Examples
title_sort creative ai through evolutionary computation: principles and examples
topic Original Research
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7986182/
https://www.ncbi.nlm.nih.gov/pubmed/33778772
http://dx.doi.org/10.1007/s42979-021-00540-9
work_keys_str_mv AT miikkulainenristo creativeaithroughevolutionarycomputationprinciplesandexamples