A Computability Perspective on (Verified) Machine Learning

A Computability Perspective on (Verified) Machine Learning

There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable an...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2021-02
Hauptverfasser: Crook, Tonicha, Morgan, Jay, Pauly, Arno, Roggenbach, Markus
Format: Artikel
Sprache:eng
Schlagworte:
Machine learning
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 Crook, Tonicha
Morgan, Jay
Pauly, Arno
Roggenbach, Markus
description There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable analysis. This allows us to define the computational tasks underlying verified ML in a model-agnostic way, and show that they are in principle computable.
format Article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2489446072</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2489446072</sourcerecordid><originalsourceid>FETCH-proquest_journals_24894460723</originalsourceid><addsrcrecordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwclRwzs8tKC1JTMrMySypVAhILSouSE0uySxLVcjPU9AISy3KTMtMTdFU8E1MzsjMS1XwSU0sysvMS-dhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXgjEwtLExMzA3MjY-JUAQCBDTZN</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2489446072</pqid></control><display><type>article</type><title>A Computability Perspective on (Verified) Machine Learning</title><source>Free E- Journals</source><creator>Crook, Tonicha ; Morgan, Jay ; Pauly, Arno ; Roggenbach, Markus</creator><creatorcontrib>Crook, Tonicha ; Morgan, Jay ; Pauly, Arno ; Roggenbach, Markus</creatorcontrib><description>There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable analysis. This allows us to define the computational tasks underlying verified ML in a model-agnostic way, and show that they are in principle computable.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Machine learning</subject><ispartof>arXiv.org, 2021-02</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by-nc-sa/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>Crook, Tonicha</creatorcontrib><creatorcontrib>Morgan, Jay</creatorcontrib><creatorcontrib>Pauly, Arno</creatorcontrib><creatorcontrib>Roggenbach, Markus</creatorcontrib><title>A Computability Perspective on (Verified) Machine Learning</title><title>arXiv.org</title><description>There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable analysis. This allows us to define the computational tasks underlying verified ML in a model-agnostic way, and show that they are in principle computable.</description><subject>Machine learning</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNpjYuA0MjY21LUwMTLiYOAtLs4yMDAwMjM3MjU15mSwclRwzs8tKC1JTMrMySypVAhILSouSE0uySxLVcjPU9AISy3KTMtMTdFU8E1MzsjMS1XwSU0sysvMS-dhYE1LzClO5YXS3AzKbq4hzh66BUX5haWpxSXxWfmlRXlAqXgjEwtLExMzA3MjY-JUAQCBDTZN</recordid><startdate>20210212</startdate><enddate>20210212</enddate><creator>Crook, Tonicha</creator><creator>Morgan, Jay</creator><creator>Pauly, Arno</creator><creator>Roggenbach, Markus</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>20210212</creationdate><title>A Computability Perspective on (Verified) Machine Learning</title><author>Crook, Tonicha ; Morgan, Jay ; Pauly, Arno ; Roggenbach, Markus</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_24894460723</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Machine learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Crook, Tonicha</creatorcontrib><creatorcontrib>Morgan, Jay</creatorcontrib><creatorcontrib>Pauly, Arno</creatorcontrib><creatorcontrib>Roggenbach, Markus</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>Crook, Tonicha</au><au>Morgan, Jay</au><au>Pauly, Arno</au><au>Roggenbach, Markus</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>A Computability Perspective on (Verified) Machine Learning</atitle><jtitle>arXiv.org</jtitle><date>2021-02-12</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>There is a strong consensus that combining the versatility of machine learning with the assurances given by formal verification is highly desirable. It is much less clear what verified machine learning should mean exactly. We consider this question from the (unexpected?) perspective of computable analysis. This allows us to define the computational tasks underlying verified ML in a model-agnostic way, and show that they are in principle computable.</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, 2021-02
issn 2331-8422
language eng
recordid cdi_proquest_journals_2489446072
source Free E- Journals
subjects Machine learning
title A Computability Perspective on (Verified) Machine Learning
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-08T21%3A26%3A04IST&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%20Computability%20Perspective%20on%20(Verified)%20Machine%20Learning&rft.jtitle=arXiv.org&rft.au=Crook,%20Tonicha&rft.date=2021-02-12&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2489446072%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2489446072&rft_id=info:pmid/&rfr_iscdi=true