PhilSci Archive

A First Contextual Taxonomy for the Opacity of AI Systems

Facchini, Alessandro and Termine, Alberto (2021) A First Contextual Taxonomy for the Opacity of AI Systems. [Preprint]

[img]
Preview
Text
Termine Facchini.pdf

Download (225kB) | Preview

Abstract

The research program of eXplainable AI (XAI) has been developed with the aim of providing tools and methods for reducing opacity and making AI systems more humanly understandable. Unfortunately, the majority of XAI scholars actually classify a system as more or less opaque by confronting it with traditional rules-based systems, which are usually assumed to be the prototype of transparent systems. In doing so, the concept of opacity remains unexplained. To overcome this issue, we propose to view opacity as a pragmatic, or contextual, concept. Based on this, we then explicit the distinction between access opacity, link opacity and semantic opacity, hence providing the groundwork for a conceptual taxonomy of the concept of opacity for AI systems.


Export/Citation: EndNote | BibTeX | Dublin Core | ASCII/Text Citation (Chicago) | HTML Citation | OpenURL
Social Networking:
Share |

Item Type: Preprint
Creators:
CreatorsEmailORCID
Facchini, Alessandroalessandro.facchini@idsia.ch0000-0001-7507-116X
Termine, Albertoalberto.termine@unimi.it0000-0001-5993-0948
Keywords: Opacity Explainable AI Taxonomy Scientific understanding
Subjects: Specific Sciences > Computation/Information > Classical
General Issues > Data
General Issues > Causation
Specific Sciences > Computer Science
General Issues > Computer Simulation
Specific Sciences > Engineering
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Technology
General Issues > Values In Science
Depositing User: Mr. Alberto Termine
Date Deposited: 19 Dec 2021 06:08
Last Modified: 19 Dec 2021 06:08
Item ID: 20040
Subjects: Specific Sciences > Computation/Information > Classical
General Issues > Data
General Issues > Causation
Specific Sciences > Computer Science
General Issues > Computer Simulation
Specific Sciences > Engineering
General Issues > Explanation
Specific Sciences > Artificial Intelligence > Machine Learning
General Issues > Technology
General Issues > Values In Science
Date: 18 December 2021
URI: http://philsci-archive.pitt.edu/id/eprint/20040

Monthly Views for the past 3 years

Monthly Downloads for the past 3 years

Plum Analytics

Actions (login required)

View Item View Item