Mathematical decisions and non-causal elements of explainable AI

10/30/2019
by   Atoosa Kasirzadeh, et al.
0

Recent conceptual discussion on the nature of the explainability of Artificial Intelligence (AI) has largely been limited to data-driven investigations. This paper identifies some shortcomings of this approach to help strengthen the debate on this subject. Building on recent philosophical work on the nature of explanations, I demonstrate the significance of two non-data driven, non-causal explanatory elements: (1) mathematical structures that are the grounds for capturing the decision-making situation; (2) statistical and optimality facts in terms of which the algorithm is designed and implemented. I argue that these elements feature directly in important aspects of AI explainability. I then propose a hierarchical framework that acknowledges the existence of various types of explanation, each of which reveals an aspect of explanation, and answers to a different kind of why-question. The usefulness of this framework will be illustrated by bringing it to bear on some salient normative concerns about the use of AI decision-making systems in society.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/24/2023

Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision support

In this paper, we argue for a paradigm shift from the current model of e...
research
05/11/2022

The Conflict Between Explainable and Accountable Decision-Making Algorithms

Decision-making algorithms are being used in important decisions, such a...
research
09/28/2018

Hows and Whys of Artificial Intelligence for Public Sector Decisions: Explanation and Evaluation

Evaluation has always been a key challenge in the development of artific...
research
01/28/2021

A Taxonomy of Explainable Bayesian Networks

Artificial Intelligence (AI), and in particular, the explainability ther...
research
06/24/2023

Manipulation Risks in Explainable AI: The Implications of the Disagreement Problem

Artificial Intelligence (AI) systems are increasingly used in high-stake...
research
04/21/2020

Explainable Goal-Driven Agents and Robots – A Comprehensive Review and New Framework

Recent applications of autonomous agents and robots, for example, self-d...
research
12/09/2021

Explainable AI for B5G/6G: Technical Aspects, Use Cases, and Research Challenges

When 5G began its commercialisation journey around 2020, the discussion ...

Please sign up or login with your details

Forgot password? Click here to reset