in the repository
URN to cite this document: urn:nbn:de:bvb:703-epub-8273-8
Title data
Kästner, Lena ; Crook, Barnaby:
Explaining AI through mechanistic interpretability.
In: European Journal for Philosophy of Science.
Vol. 14
(2024)
Issue 4
.
- 52.
ISSN 1879-4920
DOI der Verlagsversion: https://doi.org/10.1007/s13194-024-00614-4
![[thumbnail of s13194-024-00614-4.pdf]](https://epub.uni-bayreuth.de/style/images/fileicons/application_pdf.png) |
|
||||||||
|
Download (846kB)
|
Project information
| Project financing: |
VolkswagenStiftung |
|---|
Abstract
Recent work in explainable artificial intelligence (XAI) attempts to render opaque AI systems understandable through a divide-and-conquer strategy. However, this fails to illuminate how trained AI systems work as a whole. Precisely this kind of functional understanding is needed, though, to satisfy important societal desiderata such as safety. To remedy this situation, we argue, AI researchers should seek mechanistic interpretability, viz. apply coordinated discovery strategies familiar from the life sciences to uncover the functional organisation of complex AI systems. Additionally, theorists should accommodate for the unique costs and benefits of such strategies in their portrayals of XAI research.
Further data
| Item Type: | Article in a journal |
|---|---|
| Keywords: | AI; ANN; Deep learning; Discovery; Explanation; Mechanistic; interpretability; XAI |
| DDC Subjects: | 100 Philosophy and psychology > 100 Philosophy |
| Institutions of the University: | Faculties > Faculty of Cultural Studies > Department of Philosophy > Chair Philosophy, Computer Science and Artificial Intelligence > Chair Philosophy, Computer Science and Artificial Intelligence - Univ.-Prof. Dr. Lena Kästner Faculties Faculties > Faculty of Cultural Studies Faculties > Faculty of Cultural Studies > Department of Philosophy Faculties > Faculty of Cultural Studies > Department of Philosophy > Chair Philosophy, Computer Science and Artificial Intelligence |
| Language: | German |
| Originates at UBT: | Yes |
| URN: | urn:nbn:de:bvb:703-epub-8273-8 |
| Date Deposited: | 05 Mar 2025 06:12 |
| Last Modified: | 05 Mar 2025 06:12 |
| URI: | https://epub.uni-bayreuth.de/id/eprint/8273 |
Download Statistics