DeepAI AI Chat
Log In Sign Up

On Fairness and Interpretability

06/24/2021
by   Deepak P, et al.
0

Ethical AI spans a gamut of considerations. Among these, the most popular ones, fairness and interpretability, have remained largely distinct in technical pursuits. We discuss and elucidate the differences between fairness and interpretability across a variety of dimensions. Further, we develop two principles-based frameworks towards developing ethical AI for the future that embrace aspects of both fairness and interpretability. First, interpretability for fairness proposes instantiating interpretability within the realm of fairness to develop a new breed of ethical AI. Second, fairness and interpretability initiates deliberations on bringing the best aspects of both together. We hope that these two frameworks will contribute to intensifying scholarly discussions on new frontiers of ethical AI that brings together fairness and interpretability.

READ FULL TEXT

page 1

page 2

page 3

page 4

03/17/2023

CoCoMo: Computational Consciousness Modeling for Generative and Ethical AI

The CoCoMo model proposes a computational solution to the challenge of i...
04/19/2023

ACROCPoLis: A Descriptive Framework for Making Sense of Fairness

Fairness is central to the ethical and responsible development and use o...
06/13/2018

What About Applied Fairness?

Machine learning practitioners are often ambivalent about the ethical as...
03/08/2022

The Long Arc of Fairness: Formalisations and Ethical Discourse

In recent years, the idea of formalising and modelling fairness for algo...
10/10/2021

Using Edge Cases to Disentangle Fairness and Solidarity in AI Ethics

Principles of fairness and solidarity in AI ethics regularly overlap, cr...
09/20/2021

Some Critical and Ethical Perspectives on the Empirical Turn of AI Interpretability

We consider two fundamental and related issues currently faced by Artifi...
12/21/2022

A Seven-Layer Model for Standardising AI Fairness Assessment

Problem statement: Standardisation of AI fairness rules and benchmarks i...