Neuroevolution of augmented topologies with difference-based mutation
This study proposes the modification of the neuroevolution of augmented topologies, namely the difference-based mutation operator. The difference-based mutation changes the weights of the neural network by combining the weights of several other networks at the position of the connections having same...
Gespeichert in:
| Veröffentlicht in: | IOP conference series. Materials Science and Engineering 2021-02, Vol.1047 (1), p.12075 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | 1 |
| container_start_page | 12075 |
| container_title | IOP conference series. Materials Science and Engineering |
| container_volume | 1047 |
| creator | Stanovov, V Akhmedova, Sh Semenkin, E |
| description | This study proposes the modification of the neuroevolution of augmented topologies, namely the difference-based mutation operator. The difference-based mutation changes the weights of the neural network by combining the weights of several other networks at the position of the connections having same innovation numbers. The implemented neuroevolution algorithm allows backward connections and loops in the topology, and uses several mutation operators, including connections deletion. The algorithm is tested on a set of classification problems and a rotary inverted pendulum problem and compared to the same approach without difference-based mutation. The experimental results show that the proposed weight tuning scheme allows significant improvements of classification quality in several cases and finding better control algorithms. |
| doi_str_mv | 10.1088/1757-899X/1047/1/012075 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_journals_2513054883</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2513054883</sourcerecordid><originalsourceid>FETCH-LOGICAL-c3275-60c7000a4bde35a22b7869492e2dcaf393e4a748d664454fab3b39f435ff80bd3</originalsourceid><addsrcrecordid>eNqFkE1LxDAQhoMouK7-BguePNROvpr0KMv6AaseVPAW0jZZu3SbmrSK_96WyoogeJqBed534EHoFMMFBikTLLiIZZa9JBiYSHACmIDge2i2u-zvdokP0VEIG4BUMAYztLw3vXfm3dV9V7kmcjbS_Xprms6UUedaV7t1ZUL0UXWvUVlZa7xpChPnOgzAtu_0GDtGB1bXwZx8zzl6vlo-LW7i1cP17eJyFReUCB6nUAgA0CwvDeWakFzINGMZMaQstKUZNUwLJss0ZYwzq3Oa08wyyq2VkJd0js6m3ta7t96ETm1c75vhpSIcU-BMSjpQYqIK70LwxqrWV1vtPxUGNTpTow01mlGjM4XV5GxInk_JyrU_1XePy9-caks7sPQP9r8PX4_HfEA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2513054883</pqid></control><display><type>article</type><title>Neuroevolution of augmented topologies with difference-based mutation</title><source>Institute of Physics Open Access Journal Titles</source><source>Institute of Physics IOPscience extra</source><source>EZB-FREE-00999 freely available EZB journals</source><source>Free Full-Text Journals in Chemistry</source><creator>Stanovov, V ; Akhmedova, Sh ; Semenkin, E</creator><creatorcontrib>Stanovov, V ; Akhmedova, Sh ; Semenkin, E</creatorcontrib><description>This study proposes the modification of the neuroevolution of augmented topologies, namely the difference-based mutation operator. The difference-based mutation changes the weights of the neural network by combining the weights of several other networks at the position of the connections having same innovation numbers. The implemented neuroevolution algorithm allows backward connections and loops in the topology, and uses several mutation operators, including connections deletion. The algorithm is tested on a set of classification problems and a rotary inverted pendulum problem and compared to the same approach without difference-based mutation. The experimental results show that the proposed weight tuning scheme allows significant improvements of classification quality in several cases and finding better control algorithms.</description><identifier>ISSN: 1757-8981</identifier><identifier>EISSN: 1757-899X</identifier><identifier>DOI: 10.1088/1757-899X/1047/1/012075</identifier><language>eng</language><publisher>Bristol: IOP Publishing</publisher><subject>Algorithms ; Classification ; Control algorithms ; Mutation ; Network topologies ; Neural networks</subject><ispartof>IOP conference series. Materials Science and Engineering, 2021-02, Vol.1047 (1), p.12075</ispartof><rights>Published under licence by IOP Publishing Ltd</rights><rights>2021. This work is published under http://creativecommons.org/licenses/by/3.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c3275-60c7000a4bde35a22b7869492e2dcaf393e4a748d664454fab3b39f435ff80bd3</citedby><cites>FETCH-LOGICAL-c3275-60c7000a4bde35a22b7869492e2dcaf393e4a748d664454fab3b39f435ff80bd3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://iopscience.iop.org/article/10.1088/1757-899X/1047/1/012075/pdf$$EPDF$$P50$$Giop$$Hfree_for_read</linktopdf><link.rule.ids>314,780,784,27924,27925,38868,38890,53840,53867</link.rule.ids></links><search><creatorcontrib>Stanovov, V</creatorcontrib><creatorcontrib>Akhmedova, Sh</creatorcontrib><creatorcontrib>Semenkin, E</creatorcontrib><title>Neuroevolution of augmented topologies with difference-based mutation</title><title>IOP conference series. Materials Science and Engineering</title><addtitle>IOP Conf. Ser.: Mater. Sci. Eng</addtitle><description>This study proposes the modification of the neuroevolution of augmented topologies, namely the difference-based mutation operator. The difference-based mutation changes the weights of the neural network by combining the weights of several other networks at the position of the connections having same innovation numbers. The implemented neuroevolution algorithm allows backward connections and loops in the topology, and uses several mutation operators, including connections deletion. The algorithm is tested on a set of classification problems and a rotary inverted pendulum problem and compared to the same approach without difference-based mutation. The experimental results show that the proposed weight tuning scheme allows significant improvements of classification quality in several cases and finding better control algorithms.</description><subject>Algorithms</subject><subject>Classification</subject><subject>Control algorithms</subject><subject>Mutation</subject><subject>Network topologies</subject><subject>Neural networks</subject><issn>1757-8981</issn><issn>1757-899X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>O3W</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqFkE1LxDAQhoMouK7-BguePNROvpr0KMv6AaseVPAW0jZZu3SbmrSK_96WyoogeJqBed534EHoFMMFBikTLLiIZZa9JBiYSHACmIDge2i2u-zvdokP0VEIG4BUMAYztLw3vXfm3dV9V7kmcjbS_Xprms6UUedaV7t1ZUL0UXWvUVlZa7xpChPnOgzAtu_0GDtGB1bXwZx8zzl6vlo-LW7i1cP17eJyFReUCB6nUAgA0CwvDeWakFzINGMZMaQstKUZNUwLJss0ZYwzq3Oa08wyyq2VkJd0js6m3ta7t96ETm1c75vhpSIcU-BMSjpQYqIK70LwxqrWV1vtPxUGNTpTow01mlGjM4XV5GxInk_JyrU_1XePy9-caks7sPQP9r8PX4_HfEA</recordid><startdate>20210201</startdate><enddate>20210201</enddate><creator>Stanovov, V</creator><creator>Akhmedova, Sh</creator><creator>Semenkin, E</creator><general>IOP Publishing</general><scope>O3W</scope><scope>TSCCA</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>D1I</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>KB.</scope><scope>L6V</scope><scope>M7S</scope><scope>PDBOC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210201</creationdate><title>Neuroevolution of augmented topologies with difference-based mutation</title><author>Stanovov, V ; Akhmedova, Sh ; Semenkin, E</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c3275-60c7000a4bde35a22b7869492e2dcaf393e4a748d664454fab3b39f435ff80bd3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Classification</topic><topic>Control algorithms</topic><topic>Mutation</topic><topic>Network topologies</topic><topic>Neural networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Stanovov, V</creatorcontrib><creatorcontrib>Akhmedova, Sh</creatorcontrib><creatorcontrib>Semenkin, E</creatorcontrib><collection>Institute of Physics Open Access Journal Titles</collection><collection>IOPscience (Open Access)</collection><collection>CrossRef</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Materials Science Collection</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>Materials Science Database</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Materials Science Collection</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><jtitle>IOP conference series. Materials Science and Engineering</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Stanovov, V</au><au>Akhmedova, Sh</au><au>Semenkin, E</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Neuroevolution of augmented topologies with difference-based mutation</atitle><jtitle>IOP conference series. Materials Science and Engineering</jtitle><addtitle>IOP Conf. Ser.: Mater. Sci. Eng</addtitle><date>2021-02-01</date><risdate>2021</risdate><volume>1047</volume><issue>1</issue><spage>12075</spage><pages>12075-</pages><issn>1757-8981</issn><eissn>1757-899X</eissn><abstract>This study proposes the modification of the neuroevolution of augmented topologies, namely the difference-based mutation operator. The difference-based mutation changes the weights of the neural network by combining the weights of several other networks at the position of the connections having same innovation numbers. The implemented neuroevolution algorithm allows backward connections and loops in the topology, and uses several mutation operators, including connections deletion. The algorithm is tested on a set of classification problems and a rotary inverted pendulum problem and compared to the same approach without difference-based mutation. The experimental results show that the proposed weight tuning scheme allows significant improvements of classification quality in several cases and finding better control algorithms.</abstract><cop>Bristol</cop><pub>IOP Publishing</pub><doi>10.1088/1757-899X/1047/1/012075</doi><tpages>13</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1757-8981 |
| ispartof | IOP conference series. Materials Science and Engineering, 2021-02, Vol.1047 (1), p.12075 |
| issn | 1757-8981 1757-899X |
| language | eng |
| recordid | cdi_proquest_journals_2513054883 |
| source | Institute of Physics Open Access Journal Titles; Institute of Physics IOPscience extra; EZB-FREE-00999 freely available EZB journals; Free Full-Text Journals in Chemistry |
| subjects | Algorithms Classification Control algorithms Mutation Network topologies Neural networks |
| title | Neuroevolution of augmented topologies with difference-based mutation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T06%3A23%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Neuroevolution%20of%20augmented%20topologies%20with%20difference-based%20mutation&rft.jtitle=IOP%20conference%20series.%20Materials%20Science%20and%20Engineering&rft.au=Stanovov,%20V&rft.date=2021-02-01&rft.volume=1047&rft.issue=1&rft.spage=12075&rft.pages=12075-&rft.issn=1757-8981&rft.eissn=1757-899X&rft_id=info:doi/10.1088/1757-899X/1047/1/012075&rft_dat=%3Cproquest_cross%3E2513054883%3C/proquest_cross%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2513054883&rft_id=info:pmid/&rfr_iscdi=true |