An Exploration of Explainable Machine Learning Using Semantic Web Technology

The behavior of a Machine Learning (ML) algorithm is generally accepted to be a black box, i.e., it cannot be opened and understood. This paper reports on an effort to provide explanation to ML algorithms by using semantic background knowledge. A preliminary paper was found as a project seed, its ex...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:2022 IEEE 16th International Conference on Semantic Computing (ICSC) s. 143 - 146
Hlavní autori: Procko, Tyler, Elvira, Timothy, Ochoa, Omar, Del Rio, Nicholas
Médium: Konferenčný príspevok..
Jazyk:English
Vydavateľské údaje: IEEE 01.01.2022
Predmet:
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract The behavior of a Machine Learning (ML) algorithm is generally accepted to be a black box, i.e., it cannot be opened and understood. This paper reports on an effort to provide explanation to ML algorithms by using semantic background knowledge. A preliminary paper was found as a project seed, its experiment of ML explanation using the DL-Learner tool recreated and semi-automated. DL-Learner is a framework for supervised ML using background knowledge. DL-Learner induces class relationships that hold true for a positive example set. The work presented in this paper is a novel, semi-automated framework for testing the use of DL-Learner in ML explanation. A scene classifier pipeline was created to obtain test data. For the chosen dataset input to the ML, 32 trials were conducted, and explanations produced. Furthermore, this paper reports on the use of DL-Learner as a tool and the lessons learned from its use. DL-Learner, though temporally slow, may prove to be a novel means of ML explanation.
AbstractList The behavior of a Machine Learning (ML) algorithm is generally accepted to be a black box, i.e., it cannot be opened and understood. This paper reports on an effort to provide explanation to ML algorithms by using semantic background knowledge. A preliminary paper was found as a project seed, its experiment of ML explanation using the DL-Learner tool recreated and semi-automated. DL-Learner is a framework for supervised ML using background knowledge. DL-Learner induces class relationships that hold true for a positive example set. The work presented in this paper is a novel, semi-automated framework for testing the use of DL-Learner in ML explanation. A scene classifier pipeline was created to obtain test data. For the chosen dataset input to the ML, 32 trials were conducted, and explanations produced. Furthermore, this paper reports on the use of DL-Learner as a tool and the lessons learned from its use. DL-Learner, though temporally slow, may prove to be a novel means of ML explanation.
Author Ochoa, Omar
Procko, Tyler
Elvira, Timothy
Del Rio, Nicholas
Author_xml – sequence: 1
  givenname: Tyler
  surname: Procko
  fullname: Procko, Tyler
  email: prockot@my.erau.edu
  organization: Embry-Riddle Aeronautical University,United States of America
– sequence: 2
  givenname: Timothy
  surname: Elvira
  fullname: Elvira, Timothy
  email: elvirat@my.erau.edu
  organization: Embry-Riddle Aeronautical University,United States of America
– sequence: 3
  givenname: Omar
  surname: Ochoa
  fullname: Ochoa, Omar
  email: ochoao@erau.edu
  organization: Embry-Riddle Aeronautical University,United States of America
– sequence: 4
  givenname: Nicholas
  surname: Del Rio
  fullname: Del Rio, Nicholas
  email: nicholas.del_rio@afresearchlab.com
  organization: Air Force Research Lab,United States of America
BookMark eNotjLFOwzAUAI0EA5R-AQz-gYRn-8WxxyoqUCmIoa0YK8d5bi2ldpVmoH-PgC53uuUe2G3KiRh7FlAKAfZl1aybShoUpQQpSwCQ9obNbW2E1hUqFMbcs3aR-PL7NOTRTTEnnsNfuphcNxD_cP4QE_GW3Jhi2vPt-ZdrOro0Rc-_qOMb8oeUh7y_PLK74IYzza-ese3rctO8F-3n26pZtEWUoKYimE50UqEKva899AFEBz6A9rqi2mrtFSL0BmsvKk8GpdIGg8CAlQyAasae_r-RiHanMR7deNnZWmlphfoBNj5KwA
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICSC52841.2022.00029
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781665434188
166543418X
EndPage 146
ExternalDocumentID 9736291
Genre orig-research
GroupedDBID 6IE
6IL
CBEJK
RIE
RIL
ID FETCH-LOGICAL-i203t-f8b1b2343fdc7c0df01b0cf06c65e7966c3440d847c15ce8423684f14f452f043
IEDL.DBID RIE
ISICitedReferencesCount 4
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000835706300021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Thu Jun 29 18:36:55 EDT 2023
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-f8b1b2343fdc7c0df01b0cf06c65e7966c3440d847c15ce8423684f14f452f043
PageCount 4
ParticipantIDs ieee_primary_9736291
PublicationCentury 2000
PublicationDate 2022-Jan.
PublicationDateYYYYMMDD 2022-01-01
PublicationDate_xml – month: 01
  year: 2022
  text: 2022-Jan.
PublicationDecade 2020
PublicationTitle 2022 IEEE 16th International Conference on Semantic Computing (ICSC)
PublicationTitleAbbrev ICSC
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
Score 1.8489585
Snippet The behavior of a Machine Learning (ML) algorithm is generally accepted to be a black box, i.e., it cannot be opened and understood. This paper reports on an...
SourceID ieee
SourceType Publisher
StartPage 143
SubjectTerms Artificial neural networks
black box
DL-Learner
explanation
Knowledge engineering
Machine learning
Machine learning algorithms
Ontologies
semantic web
Semantics
Training
Title An Exploration of Explainable Machine Learning Using Semantic Web Technology
URI https://ieeexplore.ieee.org/document/9736291
WOSCitedRecordID wos000835706300021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LSgMxFA21uHCl0opvsnDp2GTynKUUi4KWQhW7K5PkRmbhVPrw-00yQ-vCjbskm8AJ3FfOuRehG1ApLI0kKR0SFEvLTDPIM1lKalzuSuA-DZtQ47GezYpJB91utTAAkMhncBeX6S_fLewmlsoGhQrmNkrV95SSjVarVcNRUgyehtOhCNY2Zn15asMZ48ZfM1OSyxgd_u-yI9Tfae_wZOtVjlEH6h56vq9xw5ZLQOKFT9tW-YRfEiMScNss9QMnIgCewmfArbL4HQze1dD76G308Dp8zNo5CFmVE7bOvDbU5Iwz76yyxHlCDbGeSCsFqJCvWMY5ccHPWCos6BAhSc095Z6L3BPOTlC3XtRwirCynocURoA2mgtvCskNk4Zw7oRVhT5DvYjE_KtpdTFvQTj_-_gCHUSom4rEJequlxu4Qvv2e12tltfpfX4AlSCSOg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1NTwIxEG0ImuhJDRi_7cGjK93dabd7NEQCEQgJGLkR2k4NBxeC4O-37W7AgxdvbS9NXpP56nszhDxgFsJST5KSLkHR8TySKSaRmItYmcTMEWwYNpENh3I6zUc18rjTwiBiIJ_hk1-Gv3yz1FtfKmvlmTO3Xqp-wAESVqq1Kj1czPJWrz1uc2dvfd6XhEacPnL8NTUlOI3Oyf-uOyXNvfqOjnZ-5YzUsGiQ_nNBS75cgJIubdhW2ic6CJxIpFW71A8aqAB0jJ8OuYWm76jovoreJG-dl0m7G1WTEKJFwtJNZKWKVZJCao3ONDOWxYppy4QWHDOXsegUgBnnaXTMNUoXIwkJNgYLPLEM0nNSL5YFXhCaaQsuieEolQRuVS5ApUIxAMN1lstL0vBIzFZls4tZBcLV38f35Kg7GfRn_d7w9Zoce9jL-sQNqW_WW7wlh_p7s_ha34W3-gFheJWB
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2022+IEEE+16th+International+Conference+on+Semantic+Computing+%28ICSC%29&rft.atitle=An+Exploration+of+Explainable+Machine+Learning+Using+Semantic+Web+Technology&rft.au=Procko%2C+Tyler&rft.au=Elvira%2C+Timothy&rft.au=Ochoa%2C+Omar&rft.au=Del+Rio%2C+Nicholas&rft.date=2022-01-01&rft.pub=IEEE&rft.spage=143&rft.epage=146&rft_id=info:doi/10.1109%2FICSC52841.2022.00029&rft.externalDocID=9736291