Task-Aware Neural Architecture Search

The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-03
Hauptverfasser: Le, Cat P, Soltani, Mohammadreza, Ravier, Robert, Tarokh, Vahid
Format: Artikel
Sprache:eng
Schlagworte:
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 Le, Cat P
Soltani, Mohammadreza
Ravier, Robert
Tarokh, Vahid
description The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In this paper, we propose a novel framework for neural architecture search, utilizing a dictionary of models of base tasks and the similarity between the target task and the atoms of the dictionary; hence, generating an adaptive search space based on the base models of the dictionary. By introducing a gradient-based search algorithm, we can evaluate and discover the best architecture in the search space without fully training the networks. The experimental results show the efficacy of our proposed task-aware approach.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2455098715</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2455098715</sourcerecordid><originalsourceid>FETCH-proquest_journals_24550987153</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQDUksztZ1LE8sSlXwSy0tSsxRcCxKzsgsSU0uKQWKBacmArk8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBVvZGJqamBpYW5oakycKgDcvi62</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2455098715</pqid></control><display><type>article</type><title>Task-Aware Neural Architecture Search</title><source>Free E- Journals</source><creator>Le, Cat P ; Soltani, Mohammadreza ; Ravier, Robert ; Tarokh, Vahid</creator><creatorcontrib>Le, Cat P ; Soltani, Mohammadreza ; Ravier, Robert ; Tarokh, Vahid</creatorcontrib><description>The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In this paper, we propose a novel framework for neural architecture search, utilizing a dictionary of models of base tasks and the similarity between the target task and the atoms of the dictionary; hence, generating an adaptive search space based on the base models of the dictionary. By introducing a gradient-based search algorithm, we can evaluate and discover the best architecture in the search space without fully training the networks. The experimental results show the efficacy of our proposed task-aware approach.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Adaptive search techniques ; Dictionaries ; Neural networks ; Search algorithms</subject><ispartof>arXiv.org, 2021-03</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (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>Le, Cat P</creatorcontrib><creatorcontrib>Soltani, Mohammadreza</creatorcontrib><creatorcontrib>Ravier, Robert</creatorcontrib><creatorcontrib>Tarokh, Vahid</creatorcontrib><title>Task-Aware Neural Architecture Search</title><title>arXiv.org</title><description>The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In this paper, we propose a novel framework for neural architecture search, utilizing a dictionary of models of base tasks and the similarity between the target task and the atoms of the dictionary; hence, generating an adaptive search space based on the base models of the dictionary. By introducing a gradient-based search algorithm, we can evaluate and discover the best architecture in the search space without fully training the networks. The experimental results show the efficacy of our proposed task-aware approach.</description><subject>Adaptive search techniques</subject><subject>Dictionaries</subject><subject>Neural networks</subject><subject>Search algorithms</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mRQDUksztZ1LE8sSlXwSy0tSsxRcCxKzsgsSU0uKQWKBacmArk8DKxpiTnFqbxQmptB2c01xNlDt6Aov7A0tbgkPiu_tCgPKBVvZGJqamBpYW5oakycKgDcvi62</recordid><startdate>20210315</startdate><enddate>20210315</enddate><creator>Le, Cat P</creator><creator>Soltani, Mohammadreza</creator><creator>Ravier, Robert</creator><creator>Tarokh, Vahid</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>20210315</creationdate><title>Task-Aware Neural Architecture Search</title><author>Le, Cat P ; Soltani, Mohammadreza ; Ravier, Robert ; Tarokh, Vahid</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24550987153</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Adaptive search techniques</topic><topic>Dictionaries</topic><topic>Neural networks</topic><topic>Search algorithms</topic><toplevel>online_resources</toplevel><creatorcontrib>Le, Cat P</creatorcontrib><creatorcontrib>Soltani, Mohammadreza</creatorcontrib><creatorcontrib>Ravier, Robert</creatorcontrib><creatorcontrib>Tarokh, Vahid</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>Le, Cat P</au><au>Soltani, Mohammadreza</au><au>Ravier, Robert</au><au>Tarokh, Vahid</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Task-Aware Neural Architecture Search</atitle><jtitle>arXiv.org</jtitle><date>2021-03-15</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>The design of handcrafted neural networks requires a lot of time and resources. Recent techniques in Neural Architecture Search (NAS) have proven to be competitive or better than traditional handcrafted design, although they require domain knowledge and have generally used limited search spaces. In this paper, we propose a novel framework for neural architecture search, utilizing a dictionary of models of base tasks and the similarity between the target task and the atoms of the dictionary; hence, generating an adaptive search space based on the base models of the dictionary. By introducing a gradient-based search algorithm, we can evaluate and discover the best architecture in the search space without fully training the networks. The experimental results show the efficacy of our proposed task-aware approach.</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, 2021-03
issn 2331-8422
language eng
recordid cdi_proquest_journals_2455098715
source Free E- Journals
subjects Adaptive search techniques
Dictionaries
Neural networks
Search algorithms
title Task-Aware Neural Architecture Search
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T11%3A20%3A55IST&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=Task-Aware%20Neural%20Architecture%20Search&rft.jtitle=arXiv.org&rft.au=Le,%20Cat%20P&rft.date=2021-03-15&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2455098715%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2455098715&rft_id=info:pmid/&rfr_iscdi=true