2 year post-doc position on the “Analysis, Design and Development of eXplainable Artificial Intelligence (XAI) approaches for Trustworthy Artificial Intelligence systems” at Department of Electrical Engineering and Information Technology, University of Naples Federico II.
Deadline application: 03.04.2023
The main goal of the research activity will consist in: Designing and developing Machine Learning (ML) approaches to make Artificial Intelligence (AI) systems more trustworthy, secure and transparent. This research activity will involve also the use of eXplainable Artificial Intelligence (XAI) methods, mainly investigating the following three points: 1) alleviating the dataset bias problem, 2) detecting anomalous behaviors of an already trained ML system, 3) identifying new training schemes to achieve safer and more reliable AI systems. XAI methods already known in the current literature will be explored as well as new methods will be developed.
This position is funded by the Italian Ministry of Research in the context of BRIO (BIAS, RISK, OPACITY in AI: design, verification and development of Trustworthy AI) project. (https://sites.unimi.it/brio/).
For any informal inquiry please write to guglielmo.tamburrini@unina.it.