A Hypothesis for the Aesthetic Appreciation in Neural Networks

A Hypothesis for the Aesthetic Appreciation in Neural Networks

This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts. In order to verify this hypothesis, we use multi-variate interactions to represent salient concepts and inessential concepts conta...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-07
Hauptverfasser: Xu, Cheng, Wang, Xin, Xue, Haotian, Liang, Zhengyang, Zhang, Quanshi
Format: Artikel
Sprache:eng
Schlagworte:
Hypotheses
Neural networks
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Xu, Cheng
Wang, Xin
Xue, Haotian
Liang, Zhengyang
Zhang, Quanshi
description This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts. In order to verify this hypothesis, we use multi-variate interactions to represent salient concepts and inessential concepts contained in images. Furthermore, we design a set of operations to revise images towards more beautiful ones. In experiments, we find that the revised images are more aesthetic than the original ones to some extent.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2559468735</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2559468735</sourcerecordid><originalsourceid>FETCH-proquest_journals_25594687353</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwc1TwqCzIL8lILc4sVkjLL1IAMhUcU4uBVElmsoJjQUFRanJmYklmfp5CZp6CX2ppUWIOkCopzy_KLuZhYE1LzClO5YXS3AzKbq4hzh66BUX5haVAU-Kz8kuL8oBS8UD7LE3MLMyNTY2JUwUAnHY4PA</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2559468735</pqid></control><display><type>article</type><title>A Hypothesis for the Aesthetic Appreciation in Neural Networks</title><source>Free E- Journals</source><creator>Xu, Cheng ; Wang, Xin ; Xue, Haotian ; Liang, Zhengyang ; Zhang, Quanshi</creator><creatorcontrib>Xu, Cheng ; Wang, Xin ; Xue, Haotian ; Liang, Zhengyang ; Zhang, Quanshi</creatorcontrib><description>This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts. In order to verify this hypothesis, we use multi-variate interactions to represent salient concepts and inessential concepts contained in images. Furthermore, we design a set of operations to revise images towards more beautiful ones. In experiments, we find that the revised images are more aesthetic than the original ones to some extent.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Hypotheses ; Neural networks</subject><ispartof>arXiv.org, 2021-07</ispartof><rights>2021. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Xu, Cheng</creatorcontrib><creatorcontrib>Wang, Xin</creatorcontrib><creatorcontrib>Xue, Haotian</creatorcontrib><creatorcontrib>Liang, Zhengyang</creatorcontrib><creatorcontrib>Zhang, Quanshi</creatorcontrib><title>A Hypothesis for the Aesthetic Appreciation in Neural Networks</title><title>arXiv.org</title><description>This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts. In order to verify this hypothesis, we use multi-variate interactions to represent salient concepts and inessential concepts contained in images. Furthermore, we design a set of operations to revise images towards more beautiful ones. In experiments, we find that the revised images are more aesthetic than the original ones to some extent.</description><subject>Hypotheses</subject><subject>Neural networks</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwc1TwqCzIL8lILc4sVkjLL1IAMhUcU4uBVElmsoJjQUFRanJmYklmfp5CZp6CX2ppUWIOkCopzy_KLuZhYE1LzClO5YXS3AzKbq4hzh66BUX5haVAU-Kz8kuL8oBS8UD7LE3MLMyNTY2JUwUAnHY4PA</recordid><startdate>20210731</startdate><enddate>20210731</enddate><creator>Xu, Cheng</creator><creator>Wang, Xin</creator><creator>Xue, Haotian</creator><creator>Liang, Zhengyang</creator><creator>Zhang, Quanshi</creator><general>Cornell University Library, arXiv.org</general><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>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20210731</creationdate><title>A Hypothesis for the Aesthetic Appreciation in Neural Networks</title><author>Xu, Cheng ; Wang, Xin ; Xue, Haotian ; Liang, Zhengyang ; Zhang, Quanshi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_25594687353</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Hypotheses</topic><topic>Neural networks</topic><toplevel>online_resources</toplevel><creatorcontrib>Xu, Cheng</creatorcontrib><creatorcontrib>Wang, Xin</creatorcontrib><creatorcontrib>Xue, Haotian</creatorcontrib><creatorcontrib>Liang, Zhengyang</creatorcontrib><creatorcontrib>Zhang, Quanshi</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; 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 Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</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></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xu, Cheng</au><au>Wang, Xin</au><au>Xue, Haotian</au><au>Liang, Zhengyang</au><au>Zhang, Quanshi</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Hypothesis for the Aesthetic Appreciation in Neural Networks</atitle><jtitle>arXiv.org</jtitle><date>2021-07-31</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>This paper proposes a hypothesis for the aesthetic appreciation that aesthetic images make a neural network strengthen salient concepts and discard inessential concepts. In order to verify this hypothesis, we use multi-variate interactions to represent salient concepts and inessential concepts contained in images. Furthermore, we design a set of operations to revise images towards more beautiful ones. In experiments, we find that the revised images are more aesthetic than the original ones to some extent.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2021-07
issn 2331-8422
language eng
recordid cdi_proquest_journals_2559468735
source Free E- Journals
subjects Hypotheses
Neural networks
title A Hypothesis for the Aesthetic Appreciation in Neural Networks
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T16%3A57%3A53IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=A%20Hypothesis%20for%20the%20Aesthetic%20Appreciation%20in%20Neural%20Networks&rft.jtitle=arXiv.org&rft.au=Xu,%20Cheng&rft.date=2021-07-31&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2559468735%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2559468735&rft_id=info:pmid/&rfr_iscdi=true