Moderate Adaptive Linear Units (MoLU)

Moderate Adaptive Linear Units (MoLU)

We propose a new high-performance activation function, Moderate Adaptive Linear Units (MoLU), for the deep neural network. The MoLU is a simple, beautiful and powerful activation function that can be a good main activation function among hundreds of activation functions. Because the MoLU is made up...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2024-09
Hauptverfasser: Koh, Hankyul, Joon-hyuk Ko, Jhe, Wonho
Format: Artikel
Sprache:eng
Schlagworte:
Artificial neural networks
Isomorphism
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 Koh, Hankyul
Joon-hyuk Ko
Jhe, Wonho
description We propose a new high-performance activation function, Moderate Adaptive Linear Units (MoLU), for the deep neural network. The MoLU is a simple, beautiful and powerful activation function that can be a good main activation function among hundreds of activation functions. Because the MoLU is made up of the elementary functions, not only it is a diffeomorphism (i.e. analytic over whole domains), but also it reduces the training time.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2781018526</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2781018526</sourcerecordid><originalsourceid>FETCH-proquest_journals_27810185263</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQ9c1PSS1KLElVcExJLCjJLEtV8MnMS00sUgjNyywpVtDwzfcJ1eRhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXgjcwtDA0MLUyMzY-JUAQCcsy31</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2781018526</pqid></control><display><type>article</type><title>Moderate Adaptive Linear Units (MoLU)</title><source>Free E- Journals</source><creator>Koh, Hankyul ; Joon-hyuk Ko ; Jhe, Wonho</creator><creatorcontrib>Koh, Hankyul ; Joon-hyuk Ko ; Jhe, Wonho</creatorcontrib><description>We propose a new high-performance activation function, Moderate Adaptive Linear Units (MoLU), for the deep neural network. The MoLU is a simple, beautiful and powerful activation function that can be a good main activation function among hundreds of activation functions. Because the MoLU is made up of the elementary functions, not only it is a diffeomorphism (i.e. analytic over whole domains), but also it reduces the training time.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Artificial neural networks ; Isomorphism</subject><ispartof>arXiv.org, 2024-09</ispartof><rights>2024. 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>776,780</link.rule.ids></links><search><creatorcontrib>Koh, Hankyul</creatorcontrib><creatorcontrib>Joon-hyuk Ko</creatorcontrib><creatorcontrib>Jhe, Wonho</creatorcontrib><title>Moderate Adaptive Linear Units (MoLU)</title><title>arXiv.org</title><description>We propose a new high-performance activation function, Moderate Adaptive Linear Units (MoLU), for the deep neural network. The MoLU is a simple, beautiful and powerful activation function that can be a good main activation function among hundreds of activation functions. Because the MoLU is made up of the elementary functions, not only it is a diffeomorphism (i.e. analytic over whole domains), but also it reduces the training time.</description><subject>Artificial neural networks</subject><subject>Isomorphism</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2024</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQ9c1PSS1KLElVcExJLCjJLEtV8MnMS00sUgjNyywpVtDwzfcJ1eRhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXgjcwtDA0MLUyMzY-JUAQCcsy31</recordid><startdate>20240904</startdate><enddate>20240904</enddate><creator>Koh, Hankyul</creator><creator>Joon-hyuk Ko</creator><creator>Jhe, Wonho</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>20240904</creationdate><title>Moderate Adaptive Linear Units (MoLU)</title><author>Koh, Hankyul ; Joon-hyuk Ko ; Jhe, Wonho</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_27810185263</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Artificial neural networks</topic><topic>Isomorphism</topic><toplevel>online_resources</toplevel><creatorcontrib>Koh, Hankyul</creatorcontrib><creatorcontrib>Joon-hyuk Ko</creatorcontrib><creatorcontrib>Jhe, Wonho</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>Koh, Hankyul</au><au>Joon-hyuk Ko</au><au>Jhe, Wonho</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Moderate Adaptive Linear Units (MoLU)</atitle><jtitle>arXiv.org</jtitle><date>2024-09-04</date><risdate>2024</risdate><eissn>2331-8422</eissn><abstract>We propose a new high-performance activation function, Moderate Adaptive Linear Units (MoLU), for the deep neural network. The MoLU is a simple, beautiful and powerful activation function that can be a good main activation function among hundreds of activation functions. Because the MoLU is made up of the elementary functions, not only it is a diffeomorphism (i.e. analytic over whole domains), but also it reduces the training time.</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, 2024-09
issn 2331-8422
language eng
recordid cdi_proquest_journals_2781018526
source Free E- Journals
subjects Artificial neural networks
Isomorphism
title Moderate Adaptive Linear Units (MoLU)
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-25T17%3A15%3A44IST&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=Moderate%20Adaptive%20Linear%20Units%20(MoLU)&rft.jtitle=arXiv.org&rft.au=Koh,%20Hankyul&rft.date=2024-09-04&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2781018526%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2781018526&rft_id=info:pmid/&rfr_iscdi=true