Solving the Black Box Problem: A Normative Framework for Explainable Artificial Intelligence

03/03/2019
by   Carlos Zednik, et al.
0

Many of the computing systems programmed using Machine Learning are opaque: it is difficult to know why they do what they do or how they work. The Explainable Artificial Intelligence research program aims to develop analytic techniques with which to render opaque computing systems transparent, but lacks a normative framework with which to evaluate these techniques' explanatory success. The aim of the present discussion is to develop such a framework, while paying particular attention to different stakeholders' distinct explanatory requirements. Building on an analysis of 'opacity' from philosophy of science, this framework is modeled after David Marr's influential account of explanation in cognitive science. Thus, the framework distinguishes between the different questions that might be asked about an opaque computing system, and specifies the general way in which these questions should be answered. By applying this normative framework to current techniques such as input heatmapping, feature-detector identification, and diagnostic classification, it will be possible to determine whether and to what extent the Black Box Problem can be solved.

READ FULL TEXT

page 13

page 21

research
03/03/2019

Solving the Black Box Problem: A General-Purpose Recipe for Explainable Artificial Intelligence

Many of the computing systems developed using machine learning are opaqu...
research
01/10/2021

Explainable Artificial Intelligence (XAI): An Engineering Perspective

The remarkable advancements in Deep Learning (DL) algorithms have fueled...
research
06/23/2023

Evolutionary approaches to explainable machine learning

Machine learning models are increasingly being used in critical sectors,...
research
07/20/2021

Roadmap of Designing Cognitive Metrics for Explainable Artificial Intelligence (XAI)

More recently, Explainable Artificial Intelligence (XAI) research has sh...
research
07/28/2018

Towards Explainable Inference about Object Motion using Qualitative Reasoning

The capability of making explainable inferences regarding physical proce...
research
08/20/2021

Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey

Broad Explainable Artificial Intelligence moves away from interpreting i...
research
01/28/2022

Feature Visualization within an Automated Design Assessment leveraging Explainable Artificial Intelligence Methods

Not only automation of manufacturing processes but also automation of au...

Please sign up or login with your details

Forgot password? Click here to reset