IEEE Computational Intelligence Magazine - February 2022 - 14

Guest
Editorial
Jose Maria Alonso-Moral
University of Santiago de Compostela,
SPAIN
Corrado Mencar
University of Bari Aldo Moro, ITALY
Hisao Ishibuchi
Southern University of Science and
Technology, CHINA
Explainable and Trustworthy Artificial Intelligence
I
n the era of the Internet of Things and
Big Data, data scientists are required to
extract valuable knowledge from the
given data. They first analyze, cure and
pre-process data. Then, they apply Artificial
Intelligence (AI) techniques to automatically
extract knowledge from data.
Actually, AI is identified as a strategic
technology and it is already part of our
everyday life. The European Commission
states that " EU must therefore ensure that
AI is developed and applied in an appropriate
framework which promotes innovation
and respects the Union's values and
fundamental rights as well as ethical principles
such as accountability and transparency " .
It emphasizes the importance of
eXplainable AI (XAI in short), in order to
develop an AI coherent with European
values: " to further strengthen trust, people
also need to understand how the technology
works, hence the importance of
research into the explainability of AI systems " .
Moreover, in addition to the European
General Data Protection Regulation
(GDPR), a new European regulation on
AI is in progress and it remarks once again
the need to push for a human-centric
responsible, explainable and trustworthy
AI that empowers citizens to make more
informed and thus better decisions.
In addition, as remarked in the XAI
challenge stated by the US Defense
Advanced Research Projects Agency
(DARPA), " even though current AI sysDigital
Object Identifier 10.1109/MCI.2021.3129953
Date of current version: 12 January 2022
tems offer many benefits in many applications,
their effectiveness is limited by a
lack of explanation ability when interacting
with humans " . Accordingly, humankind
requires a new generation of XAI
systems. They are expected to naturally
interact with humans, thus providing
comprehensible explanations of decisions
automatically made.
XAI is an endeavor to evolve AI
methodologies and technology by focusing
on the development of intelligent
agents capable of generating decisions that
a human could understand in a given
context, and explicitly explaining such
decisions. This way, it is possible to scrutinize
the underlying intelligent models
and verify if automated decisions are
made on the basis of accepted rules and
principles, so that decisions can be trusted
and their impact justified.
This Special Issue is supported by the
IEEE CIS Task Force on Explainable
Fuzzy Systems, with the aim of providing
readers with a holistic view of fundamentals
and current research trends in the
XAI field, paying special attention to
fuzzy-grounded knowledge representation
and reasoning but also regarding ways
to enhance human-machine interaction
through multi-modal (e.g., graphical or
textual modalities) effective explanations.
Therefore, the scope of this special issue
is not limited to the community of re -
searchers in Fuzzy Logic but it is open to
contributions by researchers, from both
academy and industry, working in the
multidisciplinary field of XAI. As a result,
14 IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE | FEBRUARY 2022
this special issue attracted 31 submissions
which reported state-of-the-art contributions
on the latest research and development,
up-to-date issues, challenges, and
applications in the field of XAI. Following
a rigorous peer review process, five papers
are finally accepted for publication.
The first paper, entitled " Towards
Understanding Human Functional Brain
Development with Explainable Artificial
Intelligence: Challenges and Perspectives " ,
by M. Kiani et al., depicts a big
picture of non-explainable and explainable
AI methods for tackling challenging
problems in Cognitive Neuroscience,
with particular emphasis on Developmental
Cognitive Neuroscience (DCN).
AI methods represent valid tools to manage
the complexity of cognitive phenomena
and can be profitably used to detect
possible cognitive developmental delays
and abnormalities; yet, current DCN
research has not benefited much from
cutting-edge methodologies (such as
deep neural networks) because of the
lack of insight offered from the designed
models. On the other hand, the adoption
of XAI-based methodologies enables the
extraction of meaningful developmental
patterns and sheds light for future medical
applications. Interestingly, the paper
highlights some limitations of current
XAI methodologies, which are inspiring
in paving the way to further research.
The second paper, entitled " PIP: Pictorial
Interpretable Prototype Learning for
Time Series Classification " by A. Ghods
and D. J. Cook, is focused on time-series
IEEE Computational Intelligence Magazine - February 2022

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - February 2022
