Dear All,
The following paper (indicated some time) ago is now accepted to ICCS
(Core A) conference.
Title: The Methods and Approaches of Explainable Artificial Intelligence
By: Szczepanski, Choras, Pawlicki, Pawlicka.
Abstract:
Since its creation, Artificial Intelligence has found innumerable
applications and become ubiquitous in everyday lives. Increasingly,
intelligent systems are being trusted with decision making; from making
unnoticeable, minor choices to determining people’s fates, e.g. as
part of predictive policing. This fact raises serious concerns about the
explainability of the systems, that is constructing the solutions is such
a way that enables humans to comprehend their results. This paper
introduces the concept of Explainable Artificial Intelligence (xAI), along
with its principles and methodology. Then, it proposes the general
taxonomy of the xAI solutions, followed by an overview of some of the
market products that utilize it.
We acknowledged SPARTA.
It should appear in June/July.
Kind Regards,
Prof. Michal Choras