Alexander Gegov

Alexander Gegov is Reader in Computational Intelligence in the School of Computing, University of Portsmouth, UK. He has been Associate Dean Research for the Faculty of Technology, University of Portsmouth, UK. He holds a PhD in Control Systems and a DSc in Intelligent Systems – both from the Bulgarian Academy of Sciences. He has been a recipient of a National Annual Award for Best Young Researcher from the Bulgarian Union of Scientists. He has been Humboldt Guest Researcher at the University of Duisburg in Germany. He has also been EU Visiting Researcher at the University of Wuppertal in Germany and the Delft University of Technology in the Netherlands.

Alexander Gegov’s research interests are in the development of computational intelligence methods and their application for modelling and simulation of complex systems and networks. He has edited 2 books and authored 4 research monographs as well asover 15 book chapters – all of these published by Springer. He hasauthoredover 50 articles and 80 papers in international journals and conferences – many of these managed and organised by the IEEE. He hasalso presented over 20 invited lectures and tutorials at International Research Events including IEEE Conferences and Summer Schools on Fuzzy Systems, Intelligent Systems, Computational Intelligence and Cybernetics.

Alexander Gegov is Associate Editor for ‘IEEE Transactions on Fuzzy Systems’, ‘Fuzzy Sets and Systems’, ‘Intelligent and Fuzzy Systems’ and ‘Computational Intelligence Systems’. He is Reviewer for several journals including IEEE journals and Assessor for several National Research Councils. He is Member of the IEEE Computational Intelligence Society and Technical Committee Member of the IEEE Society of Systems, Man and Cybernetics. He isalso Guest Editor for a forthcoming Special Issue on Deep Fuzzy Models of the IEEE Transactions on Fuzzy Systems.

Deep Fuzzy Models: Theory and Applications

Deep learning has gained significant attention within the computational intelligence community over the recent years. Its success has been mainly due to the increased capability of modern computers to collect, store and process large volumes of data. This has led to a substantial increase in the effectiveness and efficiency of data management. As a result, it has become possible to achieve high accuracy for some benchmark learning tasks such as object classification and image recognition within a short time frame. The most common implementation of deep learning has been through neural networks due to the ability of their layers to perform multiple functional composition as part of a multistage learning process.

In spite of the significant recent advances in deep learning discussed above, there are still some open problems and serious limitations. In particular, effectiveness is usually adversely affected when the data is not well defined due to inherent noise, uncertainty, ambiguity, vagueness and incompleteness. This has an adverse impact on efficiency due to the necessity to define the data better by means of additional collection, analysis and cleaning. The reduced effectiveness and efficiency undermines the ability of deep learning to address real life tasks that are safety critical or time critical. Besides this, deep leaning has been used mainly in a passive manner for the purpose of observing the environment but it almost has not been used in an active manner for the purpose of changing the environment. Finally, deep learning models often have poor transparency which makes them difficult for understanding and interpretation by non-technical users.

The problems and limitations discussed above can be addressed by means of deep fuzzy models such as hierarchical fuzzy systems and fuzzy networks. These models are well suited for performing multiple functional composition at both crisp and linguistic level. Moreover, they have the potential of handling effectively and efficiently data that is not well defined due to the use of a fuzzy approach. Also, deep fuzzy models can be used in both passive and active manner with regard to the environment due to their generic structure. Finally, these models have a high level of transparency due to their rule base nature.

The lecture will focus on the main theoretical concepts for fuzzy networks that have been recently introduced by the lecturer. The topology of these networks is described by nodes that are rule bases and connections that are outputs from rule bases fed as inputs to the same or other rule bases. Node level modelling is done by Boolean matrices or binary relations whereas network level modelling is done by block schemes or topological expressions. Several types of fuzzy networks are considered such multilevel, multilayer, feedforward and feedback in the context of analysis and design by means of node merging and splitting operations. The theoretical results are applied to several case studiesand validated against other models with regard to performance indicators such as accuracy, efficiency, transparency and feasibility.