Alexander Gegov, University of Portsmouth / Technical University of Sofia, alexander.gegov@port.ac.uk, https://www.port.ac.uk/about-us/structure-and-governance/our-people/our-staff/alexander-gegov

Farzad Arabikhan, University of Portsmouth, farzad.arabikhan@port.ac.uk, https://www.port.ac.uk/about-us/structure-and-governance/our-people/our-staff/farzad-arabikhan

Tutorial Abstract

Fuzzy network models are like neural network models in terms of general structure. However, their nodes and connections are different. The nodes of fuzzy network models are fuzzy rule bases and the connections between the nodes are outputs from and inputs to these rule bases. In this context, apart from being a structural counterpart for a neural network, a fuzzy network model is also a conceptual generalisation of a fuzzy system model as well as bridge between two established types of fuzzy system models – flat and hierarchical. 

Tutorial description

Learning Objectives: The main goal of this tutorial is to make the conference participants familiar with fuzzy network models and their inherent interpretability which makes them suitable for explainable artificial intelligence. These models facilitate the identification of causal relationships between external inputs and outputs by means of intermediate variables. 

Tutorial Outline:  The tutorial is planned for two hours and it has two halves – theory and applications of fuzzy network models. The material will be presented consistently at a general level whereby theoretical concepts will be briefly introduced mathematically and then illustrated visually. Fuzzy network models have an underlying two-dimensional grid structure with horizontal levels and vertical layers. The levels represent spatial hierarchy in terms of breadth and the layers represent temporal hierarchy in terms of depth. The nodes of fuzzy network models are described by Boolean matrices or binary relations. The connections between the nodes are described by block schemes or topological expressions. Each node is located in a cell within the underlying grid structure. Nodes in fuzzy network models are manipulated by merging and splitting operations. The merging operations are for network model analysis and the splitting operations are for network model design. These operations are used for converting fuzzy network models into fuzzy system models and vice versa. The operations are illustrated on feedforward and feedback fuzzy network models. Feedforward fuzzy network models include combinations of narrow/wide and shallow/deep structures. Feedback fuzzy network models include combinations of single/multiple and local/global feedback. Fuzzy network models are applied to several benchmark examples and validated successfully against flat and hierarchical fuzzy system models. The validation uses performance evaluation indicators for feasibility, accuracy, efficiency, transparency. In addition to the theoretical concepts above, the tutorial will also present case studies on the application of fuzzy network models. The case studies are benchmarked against flat and hierarchical fuzzy system models. Expected audience size: The tutorial is expected to be attended by at least 50 conference participants in view of the current high popularity of explainable artificial intelligence, the exponential growth in the number of recent publications in this area and the inherent interpretability of fuzzy network models in terms of their rule-based structure 

Tutorial Organisers

Alexander Gegov is Associate Professor in Computational Intelligence in the School of Computing at the University of Portsmouth. He is also Visiting Professor in Control Theory in the English Faculty of Engineering at the Technical University of Sofia. He holds a PhD in Cybernetics and a DSc in Artificial Intelligence – both from the Bulgarian Academy of Sciences. He has been a recipient of a national award for Best Young Researcher from the Bulgarian Union of Scientists. He has been Humboldt Guest Researcher at the Universities of Duisburg and Wuppertal in Germany. He has also been EU Visiting Researcher at the Delft University of Technology in the Netherlands.

Alexander Gegov’s research interests are in the development of artificial intelligence and machine learning methods as well as their application for modelling and simulation of complex systems and networks. He has guest edited several special issues of journals and books with conference proceeding published by IEEE and Springer. He has authored 5 research monographs and more than 20 book chapters published by Springer. He has also authored more than 100 articles and papers in a wide range of peer-reviewed specialised journals and international conferences including IEEE journals and conferences. He has presented more than 20 invited lectures and tutorials at international scientific events including IEEE, EPSRC and NATO Conferences and Summer Schools on Artificial Intelligence, Fuzzy Systems, Neural Networks, Intelligent Systems, Computational Intelligence, Cybernetics and Complexity Science.

Alexander Gegov is Associate Editor for the IEEE Transactions on Artificial Intelligence, IEEE Transactions on Fuzzy Systems, the International Journal of Intelligent Systems, the Journal of Fuzzy Sets and Systems and the International Journal of Computational Intelligence Systems. He is currently Member of the Soft Computing Technical Committee of the IEEE Society of Systems, Man and Cybernetics and the Outstanding Paper Award Committee for IEEE Transactions on Fuzzy Systems of the IEEE Computational Intelligence Society. He is also Member of the IEEE Working Groups on Explainable Artificial Intelligence and Trustworthy Artificial Intelligence as well as the IEEE Task Forces on Explainable Fuzzy Systems and Fuzzy Systems Software.

Farzad Arabikhan joined the University of Portsmouth, UK, as a Lecturer in 2017 after completing his PhD on Modelling Telecommuting using Fuzzy Networks at the same university.  He is now a Senior Lecturer and the course leader of BSc Data Science and Analytics program. He has published his research results in several journal articles and conference papers. He has been involved in number of projects totalling around £22 million mainly from Innovate UK where the focus has been the application of AI in decarbonisation and transport. He has also secured funding from the EU COST Programme for research collaboration with leading academics at the Paris-Sorbonne University, France and the Mediterranean University of Reggio Calabria, Italy. He holds BSc and MSc degrees in Civil Engineering and Transportation Engineering from the Sharif University of Technology, Tehran, Iran.