Assoc. Prof. Alexander Gegov, PhD, DSc
Explainable Artificial Intelligence: A Surrogate Modelling Approach
Associate Professor of Computational Intelligence, School of Computing, Mathematics and Physics, University of Portsmouth, United Kingdom · Visiting Professor of Control Theory, English Language Faculty of Engineering, Technical University of Sofia
Machine Learning has recently established itself as the main approach to designing and implementing AI. However, in spite of the significant improvement in the accuracy of predictions, most ML models suffer from lack of interpretability and the recommendations made by most AI systems suffer from lack of explainability. This is a significant problem especially for safety critical applications where wrong recommendations from an AI system may have serious consequences.
The presentation will highlight recent developments in Explainable AI. It will also focus on Surrogate Modelling as a promising research trend that is aimed at finding a good balance between accuracy and explainability of machine learning models used in AI systems. This balance guarantees reliable and understandable solutions that improve some AI features such as safety and trustworthiness. These features can facilitate and speed up the successful adoption of AI on a wider scale.
About the speaker
Alexander Gegov is currently Associate Professor of Computational Intelligence in the School of Computing, Maths and Physics at the University of Portsmouth and Visiting Professor of Control Theory in the English Language Faculty of Engineering at the Technical University of Sofia. In the past, he has held research positions at the Delft University of Technology, the University of Wuppertal, the University of Duisburg and the Bulgarian Academy of Sciences. He holds a PhD in Control Systems and a DSc in Artificial Intelligence.
His research interests include machine learning, artificial intelligence and complex systems. His work involves the development and application of machine learning models and artificial intelligence systems for modelling and simulation of complex systems. He has more than 200 peer-reviewed publications including research monographs, book chapters, journal articles and conference papers. He is also Associate Editor for IEEE Transactions on Artificial Intelligence and IEEE Transactions on Fuzzy Systems.