Skoči na glavni sadržaj

Izvorni znanstveni članak

https://doi.org/10.21464/sp38203

Unexplainable Explainable AI

Hyeongjoo Kim orcid id orcid.org/0000-0001-8049-6277 ; Chung-Ang University, Humanities Research Institute, 84 Heukseok-ro, Dongjak-gu, KR–06974 Seoul


Puni tekst: engleski pdf 1.123 Kb

str. 275-295

preuzimanja: 336

citiraj


Sažetak

This paper critically investigates the explainable artificial intelligence (XAI) project. I analyze the word “explain” in XAI and the theory of explanation and identify the discrepancy between the meaning of the explanation claimed to be necessary and that which is actually presented. After summarizing the history of AI related to explainability, I argue that American philosophy in the 1900s operated in the background of said history. I then extract the meaning of explanation in view of XAI, to elucidate the relationship among AI, logic, and the theory of explanation. In so doing, I aim to reveal DARPA’s surreptitious definitional retreat in terms of its contents and formal fallacy of sophisma figurae dictionis, drawing from Kant’s paralogism. I conclude that this intentional fallacy preexists the XAI project and that presumptuous use of reason, which Kant criticizes, is underlying.

Ključne riječi

XAI; AI; explanation; paralogism; sophisma figurae dictionis; Immanuel Kant

Hrčak ID:

314451

URI

https://hrcak.srce.hr/314451

Datum izdavanja:

29.12.2023.

Podaci na drugim jezicima: hrvatski njemački francuski

Posjeta: 1.302 *