Dear Colleagues,

With the steady increase in the use of Artificial Intelligence (AI) and Machine Learning (ML) technologies in various domains, such as Cybersecurity, Helthcare and Transportation, there is a need to make AI and ML algorithms more accessible and easier to develop.

AI and ML algorithms require experts to invest in time to develop models that people can use in their respective domains. Black-box algorithm development allows people to use such models, but these cannot be interpreted, whereas White-box algorithms are interpretable to a certain extent.

This SI focuses on both theoretical and practical aspects of White-box Artificial Intelligence and Machine Learning. Particularly, we are looking for approaches that can facilitate algorithm development to make it less time consuming for developers and enchance the transparency.

Topics of interest include, but are not limited to:

Enchancing usability between AI or ML systems and humans;
Explainability of AI or ML algorithms;
Transparent AI or ML algorithms;
Evaluation metrics;
Visualization techniques;
User interfaces that facilitate algorithm development (GUIs, NLP, Chatbots);
Automated code generation;
Novel applications of Human-Centred AI or ML;
Trust, Privacy and Security Issues;
Experiences with the development of industrial ML systems;
Evaluation of programming languages and libraries when developing ML systems.

Dr. Nikolaos Polatidis
Prof. Marcello Trovati
Prof. Dr. Emiliano Tramontana
Guest Editors