Interpretability and Unification.
Saved in:
| Title: | Interpretability and Unification. |
|---|---|
| Authors: | Erasmus, Adrian1,2 (AUTHOR) aderasmus@ua.edu, Brunet, T. D. P.3 (AUTHOR) |
| Source: | Philosophy & Technology. Jun2022, Vol. 35 Issue 2, p1-6. 6p. |
| Abstract: | In a recent reply to our article, “What is Interpretability?,” Prasetya argues against our position that artificial neural networks are explainable. It is claimed that our indefeasibility thesis—that adding complexity to an explanation of a phenomenon does not make the phenomenon any less explainable—is false. More precisely, Prasetya argues that unificationist explanations are defeasible to increasing complexity, and thus, we may not be able to provide such explanations of highly complex AI models. The reply highlights an important lacuna in our original paper, the omission of the unificationist account of explanation, and affords us the opportunity to respond. Here, we argue that artificial neural networks are explainable in a way that should satisfy unificationists and that interpretability methods present ways in which ML theories can achieve unification. [ABSTRACT FROM AUTHOR] |
| Copyright of Philosophy & Technology is the property of Springer Nature 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: | Education Research Complete |
| FullText | Text: Availability: 0 |
|---|---|
| Header | DbId: ehh DbLabel: Education Research Complete An: 156490948 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Interpretability and Unification. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Erasmus%2C+Adrian%22">Erasmus, Adrian</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> aderasmus@ua.edu</i><br /><searchLink fieldCode="AR" term="%22Brunet%2C+T%2E+D%2E+P%2E%22">Brunet, T. D. P.</searchLink><relatesTo>3</relatesTo> (AUTHOR) – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Philosophy+%26+Technology%22">Philosophy & Technology</searchLink>. Jun2022, Vol. 35 Issue 2, p1-6. 6p. – Name: Abstract Label: Abstract Group: Ab Data: In a recent reply to our article, “What is Interpretability?,” Prasetya argues against our position that artificial neural networks are explainable. It is claimed that our indefeasibility thesis—that adding complexity to an explanation of a phenomenon does not make the phenomenon any less explainable—is false. More precisely, Prasetya argues that unificationist explanations are defeasible to increasing complexity, and thus, we may not be able to provide such explanations of highly complex AI models. The reply highlights an important lacuna in our original paper, the omission of the unificationist account of explanation, and affords us the opportunity to respond. Here, we argue that artificial neural networks are explainable in a way that should satisfy unificationists and that interpretability methods present ways in which ML theories can achieve unification. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Philosophy & Technology is the property of Springer Nature 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=ehh&AN=156490948 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s13347-022-00537-z Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 6 StartPage: 1 Titles: – TitleFull: Interpretability and Unification. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Erasmus, Adrian – PersonEntity: Name: NameFull: Brunet, T. D. P. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 06 Text: Jun2022 Type: published Y: 2022 Identifiers: – Type: issn-print Value: 22105433 Numbering: – Type: volume Value: 35 – Type: issue Value: 2 Titles: – TitleFull: Philosophy & Technology Type: main |
| ResultId | 1 |
