Interpretable machine learning aims at unveiling the reasons behind predictions returned by
uninterpretable classifiers. One of the most valuable types of explanation consists of …

Machine learning is increasingly used to inform decision making in sensitive situations
where decisions have consequential effects on individuals' lives. In these settings, in …

Most of state of the art methods applied on time series consist of deep learning methods that
are too complex to be interpreted. This lack of interpretability is a major drawback, as several …

Machine learning plays a role in many deployed decision systems, often in ways that are
difficult or impossible to understand by human stakeholders. Explaining, in a human …

Machine learning is increasingly used to inform decision-making in sensitive situations
where decisions have consequential effects on individuals' lives. In these settings, in …

Time series data is increasingly used in a wide range of fields, and it is often relied on in
crucial applications and high-stakes decision-making. For instance, sensors generate time …

In recent years, there has been a rapidly expanding focus on explaining the predictions
made by black-box AI systems that handle image and tabular data. However, considerably …

With the advent of 5G commercialization, the need for more reliable, faster, and intelligent
telecommunication systems is envisaged for the next generation beyond 5G (B5G) radio …

End-to-end deep learning models are increasingly applied to safety-critical human activity
recognition (HAR) applications, eg, healthcare monitoring and smart home control, to reduce …

The field of eXplainable Artificial Intelligence (XAI) has witnessed significant advancements
in recent years. However, the majority of progress has been concentrated in the domains of …