Neuroevolution: from architectures to learning

Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm h...

Full description

Saved in:
Bibliographic Details
Published in:Evolutionary intelligence 2008-03, Vol.1 (1), p.47-62
Main Authors: Floreano, Dario, Dürr, Peter, Mattiussi, Claudio
Format: Article
Language:English
Subjects:
Applications of Mathematics
Artificial Intelligence
Bioinformatics
Control
Engineering
Mathematical and Computational Engineering
Mechatronics
Review Article
Robotics
Statistical Physics and Dynamical Systems
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c354t-f69935b71bfab07a35ba05ff5f76d29c5cc7bee2aa3c500130362f1547ef5ba63
cites cdi_FETCH-LOGICAL-c354t-f69935b71bfab07a35ba05ff5f76d29c5cc7bee2aa3c500130362f1547ef5ba63
container_end_page 62
container_issue 1
container_start_page 47
container_title Evolutionary intelligence
container_volume 1
creator Floreano, Dario
Dürr, Peter
Mattiussi, Claudio
description Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm have to be addressed. Evolutionary search methods can provide an automatic solution to these problems. New insights in both neuroscience and evolutionary biology have led to the development of increasingly powerful neuroevolution techniques over the last decade. This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures.
doi_str_mv 10.1007/s12065-007-0002-4
format article
fullrecord <record><control><sourceid>crossref_sprin</sourceid><recordid>TN_cdi_crossref_primary_10_1007_s12065_007_0002_4</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>10_1007_s12065_007_0002_4</sourcerecordid><originalsourceid>FETCH-LOGICAL-c354t-f69935b71bfab07a35ba05ff5f76d29c5cc7bee2aa3c500130362f1547ef5ba63</originalsourceid><addsrcrecordid>eNp9j8tOwzAQRS0EEqXlA9jlB1zGb8IOVbykCjZ0bTnGLqnSGI0TJP4eR0EsWYzmLO4ZzSXkisGaAZjrzDhoRQuWAU7lCVmwGy2pqpk5_WOoz8lFzgcAzcHIBVm_hBFT-ErdOLSpv60ipmPl0H-0Q_DDiCFXQ6q64LBv-_2KnEXX5XD5u5dk93D_tnmi29fH583dlnqh5ECjrmuhGsOa6BowrrADFaOKRr_z2ivvTRMCd054BcAECM0jU9KEWKJaLAmb73pMOWOI9hPbo8Nvy8BOhe1c2E44FbayOHx2csn2-4D2kEbsy5v_SD-Qb1jr</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Neuroevolution: from architectures to learning</title><source>Springer Link</source><creator>Floreano, Dario ; Dürr, Peter ; Mattiussi, Claudio</creator><creatorcontrib>Floreano, Dario ; Dürr, Peter ; Mattiussi, Claudio</creatorcontrib><description>Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm have to be addressed. Evolutionary search methods can provide an automatic solution to these problems. New insights in both neuroscience and evolutionary biology have led to the development of increasingly powerful neuroevolution techniques over the last decade. This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures.</description><identifier>ISSN: 1864-5909</identifier><identifier>EISSN: 1864-5917</identifier><identifier>DOI: 10.1007/s12065-007-0002-4</identifier><language>eng</language><publisher>Berlin/Heidelberg: Springer-Verlag</publisher><subject>Applications of Mathematics ; Artificial Intelligence ; Bioinformatics ; Control ; Engineering ; Mathematical and Computational Engineering ; Mechatronics ; Review Article ; Robotics ; Statistical Physics and Dynamical Systems</subject><ispartof>Evolutionary intelligence, 2008-03, Vol.1 (1), p.47-62</ispartof><rights>Springer-Verlag 2008</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c354t-f69935b71bfab07a35ba05ff5f76d29c5cc7bee2aa3c500130362f1547ef5ba63</citedby><cites>FETCH-LOGICAL-c354t-f69935b71bfab07a35ba05ff5f76d29c5cc7bee2aa3c500130362f1547ef5ba63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>314,780,784,27924,27925</link.rule.ids></links><search><creatorcontrib>Floreano, Dario</creatorcontrib><creatorcontrib>Dürr, Peter</creatorcontrib><creatorcontrib>Mattiussi, Claudio</creatorcontrib><title>Neuroevolution: from architectures to learning</title><title>Evolutionary intelligence</title><addtitle>Evol. Intel</addtitle><description>Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm have to be addressed. Evolutionary search methods can provide an automatic solution to these problems. New insights in both neuroscience and evolutionary biology have led to the development of increasingly powerful neuroevolution techniques over the last decade. This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures.</description><subject>Applications of Mathematics</subject><subject>Artificial Intelligence</subject><subject>Bioinformatics</subject><subject>Control</subject><subject>Engineering</subject><subject>Mathematical and Computational Engineering</subject><subject>Mechatronics</subject><subject>Review Article</subject><subject>Robotics</subject><subject>Statistical Physics and Dynamical Systems</subject><issn>1864-5909</issn><issn>1864-5917</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><recordid>eNp9j8tOwzAQRS0EEqXlA9jlB1zGb8IOVbykCjZ0bTnGLqnSGI0TJP4eR0EsWYzmLO4ZzSXkisGaAZjrzDhoRQuWAU7lCVmwGy2pqpk5_WOoz8lFzgcAzcHIBVm_hBFT-ErdOLSpv60ipmPl0H-0Q_DDiCFXQ6q64LBv-_2KnEXX5XD5u5dk93D_tnmi29fH583dlnqh5ECjrmuhGsOa6BowrrADFaOKRr_z2ivvTRMCd054BcAECM0jU9KEWKJaLAmb73pMOWOI9hPbo8Nvy8BOhe1c2E44FbayOHx2csn2-4D2kEbsy5v_SD-Qb1jr</recordid><startdate>20080301</startdate><enddate>20080301</enddate><creator>Floreano, Dario</creator><creator>Dürr, Peter</creator><creator>Mattiussi, Claudio</creator><general>Springer-Verlag</general><scope>AAYXX</scope><scope>CITATION</scope></search><sort><creationdate>20080301</creationdate><title>Neuroevolution: from architectures to learning</title><author>Floreano, Dario ; Dürr, Peter ; Mattiussi, Claudio</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c354t-f69935b71bfab07a35ba05ff5f76d29c5cc7bee2aa3c500130362f1547ef5ba63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Applications of Mathematics</topic><topic>Artificial Intelligence</topic><topic>Bioinformatics</topic><topic>Control</topic><topic>Engineering</topic><topic>Mathematical and Computational Engineering</topic><topic>Mechatronics</topic><topic>Review Article</topic><topic>Robotics</topic><topic>Statistical Physics and Dynamical Systems</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Floreano, Dario</creatorcontrib><creatorcontrib>Dürr, Peter</creatorcontrib><creatorcontrib>Mattiussi, Claudio</creatorcontrib><collection>CrossRef</collection><jtitle>Evolutionary intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Floreano, Dario</au><au>Dürr, Peter</au><au>Mattiussi, Claudio</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Neuroevolution: from architectures to learning</atitle><jtitle>Evolutionary intelligence</jtitle><stitle>Evol. Intel</stitle><date>2008-03-01</date><risdate>2008</risdate><volume>1</volume><issue>1</issue><spage>47</spage><epage>62</epage><pages>47-62</pages><issn>1864-5909</issn><eissn>1864-5917</eissn><abstract>Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm have to be addressed. Evolutionary search methods can provide an automatic solution to these problems. New insights in both neuroscience and evolutionary biology have led to the development of increasingly powerful neuroevolution techniques over the last decade. This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures.</abstract><cop>Berlin/Heidelberg</cop><pub>Springer-Verlag</pub><doi>10.1007/s12065-007-0002-4</doi><tpages>16</tpages></addata></record>
fulltext fulltext
identifier ISSN: 1864-5909
ispartof Evolutionary intelligence, 2008-03, Vol.1 (1), p.47-62
issn 1864-5909
1864-5917
language eng
recordid cdi_crossref_primary_10_1007_s12065_007_0002_4
source Springer Link
subjects Applications of Mathematics
Artificial Intelligence
Bioinformatics
Control
Engineering
Mathematical and Computational Engineering
Mechatronics
Review Article
Robotics
Statistical Physics and Dynamical Systems
title Neuroevolution: from architectures to learning
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T08%3A24%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-crossref_sprin&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Neuroevolution:%20from%20architectures%20to%20learning&rft.jtitle=Evolutionary%20intelligence&rft.au=Floreano,%20Dario&rft.date=2008-03-01&rft.volume=1&rft.issue=1&rft.spage=47&rft.epage=62&rft.pages=47-62&rft.issn=1864-5909&rft.eissn=1864-5917&rft_id=info:doi/10.1007/s12065-007-0002-4&rft_dat=%3Ccrossref_sprin%3E10_1007_s12065_007_0002_4%3C/crossref_sprin%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c354t-f69935b71bfab07a35ba05ff5f76d29c5cc7bee2aa3c500130362f1547ef5ba63%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true