Explainable Artificial Intelligence

Black box AI systems for automated decision making, often based on machine learning over (big) data, map a user’s features into a class or a score without exposing the reasons why. This is problematic not only for the lack of transparency, but also for possible biases inherited by the algorithms from human prejudices and collection artifacts hidden in the training data, which may lead to unfair or wrong decisions. The future of AI lies in enabling people to collaborate with machines to solve complex problems. Like any efficient collaboration, this requires good communication, trust, clarity and understanding. Explainable AI addresses such challenges and for years different AI communities have studied such topic, leading to different definitions, evaluation protocols, motivations, and results.   This (30 hours) course provides a reasoned introduction to the work of Explainable AI (XAI) to date, and surveys the literature with a focus on post-hoc and by-design approaches.  We motivate the needs of XAI in real-world and large-scale application, while presenting state-of-the-art techniques and best practices, as well as discussing the many open challenges. An XAI platform with collection of many of the recently proposed algorithms will be presented on specific use cases and it will be possible familiarize with some of the methods. 

The course is organized as follows in three modules: i) an introductory one providing motivations, main concepts and main methods; ii) an advanced one where the students will actively participate to monographs topics with readings interleaved with interventions of international scholars working on the sector; iii) an hands-on module where the students will be introduced to the usage on XAI methods.