Academic Journal
The Cost of Understanding—XAI Algorithms towards Sustainable ML in the View of Computational Cost.
| Title: | The Cost of Understanding—XAI Algorithms towards Sustainable ML in the View of Computational Cost. |
|---|---|
| Authors: | Jean-Quartier, Claire, Bein, Katharina, Hejny, Lukas, Hofer, Edith, Holzinger, Andreas, Jeanquartier, Fleur |
| Source: | Computation; May2023, Vol. 11 Issue 5, p92, 14p |
| Subject Terms: | Artificial intelligence, Computer vision, Algorithms, Energy consumption, Consumption (Economics), Python programming language |
| Abstract: | In response to socioeconomic development, the number of machine learning applications has increased, along with the calls for algorithmic transparency and further sustainability in terms of energy efficient technologies. Modern computer algorithms that process large amounts of information, particularly artificial intelligence methods and their workhorse machine learning, can be used to promote and support sustainability; however, they consume a lot of energy themselves. This work focuses and interconnects two key aspects of artificial intelligence regarding the transparency and sustainability of model development. We identify frameworks for measuring carbon emissions from Python algorithms and evaluate energy consumption during model development. Additionally, we test the impact of explainability on algorithmic energy consumption during model optimization, particularly for applications in health and, to expand the scope and achieve a widespread use, civil engineering and computer vision. Specifically, we present three different models of classification, regression and object-based detection for the scenarios of cancer classification, building energy, and image detection, each integrated with explainable artificial intelligence (XAI) or feature reduction. This work can serve as a guide for selecting a tool to measure and scrutinize algorithmic energy consumption and raise awareness of emission-based model optimization by highlighting the sustainability of XAI. [ABSTRACT FROM AUTHOR] |
| Copyright of Computation is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Biomedical Index |
| FullText | Text: Availability: 0 CustomLinks: – Url: https://resolver.ebsco.com/c/fiv2js/result?sid=EBSCO:edm&genre=article&issn=20793197&ISBN=&volume=11&issue=5&date=20230501&spage=92&pages=92-105&title=Computation&atitle=The%20Cost%20of%20Understanding%E2%80%94XAI%20Algorithms%20towards%20Sustainable%20ML%20in%20the%20View%20of%20Computational%20Cost.&aulast=Jean-Quartier%2C%20Claire&id=DOI:10.3390/computation11050092 Name: Full Text Finder (for New FTF UI) (ns324271) Category: fullText Text: Full Text Finder MouseOverText: Full Text Finder |
|---|---|
| Header | DbId: edm DbLabel: Biomedical Index An: 163937809 RelevancyScore: 932 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 931.955322265625 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: The Cost of Understanding—XAI Algorithms towards Sustainable ML in the View of Computational Cost. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Jean-Quartier%2C+Claire%22">Jean-Quartier, Claire</searchLink><br /><searchLink fieldCode="AR" term="%22Bein%2C+Katharina%22">Bein, Katharina</searchLink><br /><searchLink fieldCode="AR" term="%22Hejny%2C+Lukas%22">Hejny, Lukas</searchLink><br /><searchLink fieldCode="AR" term="%22Hofer%2C+Edith%22">Hofer, Edith</searchLink><br /><searchLink fieldCode="AR" term="%22Holzinger%2C+Andreas%22">Holzinger, Andreas</searchLink><br /><searchLink fieldCode="AR" term="%22Jeanquartier%2C+Fleur%22">Jeanquartier, Fleur</searchLink> – Name: TitleSource Label: Source Group: Src Data: Computation; May2023, Vol. 11 Issue 5, p92, 14p – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Computer+vision%22">Computer vision</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithms%22">Algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Energy+consumption%22">Energy consumption</searchLink><br /><searchLink fieldCode="DE" term="%22Consumption+%28Economics%29%22">Consumption (Economics)</searchLink><br /><searchLink fieldCode="DE" term="%22Python+programming+language%22">Python programming language</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: In response to socioeconomic development, the number of machine learning applications has increased, along with the calls for algorithmic transparency and further sustainability in terms of energy efficient technologies. Modern computer algorithms that process large amounts of information, particularly artificial intelligence methods and their workhorse machine learning, can be used to promote and support sustainability; however, they consume a lot of energy themselves. This work focuses and interconnects two key aspects of artificial intelligence regarding the transparency and sustainability of model development. We identify frameworks for measuring carbon emissions from Python algorithms and evaluate energy consumption during model development. Additionally, we test the impact of explainability on algorithmic energy consumption during model optimization, particularly for applications in health and, to expand the scope and achieve a widespread use, civil engineering and computer vision. Specifically, we present three different models of classification, regression and object-based detection for the scenarios of cancer classification, building energy, and image detection, each integrated with explainable artificial intelligence (XAI) or feature reduction. This work can serve as a guide for selecting a tool to measure and scrutinize algorithmic energy consumption and raise awareness of emission-based model optimization by highlighting the sustainability of XAI. [ABSTRACT FROM AUTHOR] – Name: Abstract Label: Group: Ab Data: <i>Copyright of Computation is the property of MDPI and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edm&AN=163937809 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.3390/computation11050092 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 14 StartPage: 92 Subjects: – SubjectFull: Artificial intelligence Type: general – SubjectFull: Computer vision Type: general – SubjectFull: Algorithms Type: general – SubjectFull: Energy consumption Type: general – SubjectFull: Consumption (Economics) Type: general – SubjectFull: Python programming language Type: general Titles: – TitleFull: The Cost of Understanding—XAI Algorithms towards Sustainable ML in the View of Computational Cost. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Jean-Quartier, Claire – PersonEntity: Name: NameFull: Bein, Katharina – PersonEntity: Name: NameFull: Hejny, Lukas – PersonEntity: Name: NameFull: Hofer, Edith – PersonEntity: Name: NameFull: Holzinger, Andreas – PersonEntity: Name: NameFull: Jeanquartier, Fleur IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 05 Text: May2023 Type: published Y: 2023 Identifiers: – Type: issn-print Value: 20793197 Numbering: – Type: volume Value: 11 – Type: issue Value: 5 Titles: – TitleFull: Computation Type: main |
| ResultId | 1 |