Explainable AI - Usable explanations in industrial and critical environments

In recent years, using proxies to demystify black-box algorithms has gained popularity and become a standard methodology in industrial environments. However, there are still challenges in interpreting the results and generalising these explanations in critical scenarios where accuracy and transparency are paramount.

Programa

Introduction to Explainable AI (XAI).
Limitation of current XAI techniques in terms of interpretability
Features of usable explanations in critical environments.
Future trends in XAI.

Masterclass taught by the i2Cat Foundation

Play video Download Presentation

Taught by:

ALBERT CALVO

Senior AI & Cyber Researcher, i2CAT Foundation

Albert Calvo works as an AI Researcher at the i2Cat Foundation in the Department of Distributed Artificial Intelligence (DAI) and is also an associate professor in the Department of Computer Science at the UPC (Polytechnic University of Catalonia). Albert is a computer engineer specialising in Information Technologies. He also pursued a Master’s degree in Computer Science, where he conducted his master’s thesis at EPFL (École polytechnique fédérale de Lausanne). Currently, Albert is a doctoral candidate in computer science at the UPC. His research focuses on Explainability in industrial projects related to Data Science, aiming to build solutions that meet the requirements of transparency and robustness, allowing them to be used seamlessly by the end user. The researcher has also authored publications in internationally renowned conferences and journals in the field of Artificial Intelligence, including ECAI, DSAA, and Data Mining and Knowledge Discovery, as well as presentations at cybersecurity conferences such as FIRST and eCrime Symposium.