Abstract : Informed Machine Learning: Emerging Opportunities
Machine Learning (ML) and Artificial Intelligence (AI) have enjoyed a lot of interest and led to numerous success stories including those in areas of high criticality. With the passage of time, some limitations of the ML technology have become visible and raised concerns about the deployment of the ML constructs (including LLMs) and their exclusive reliance on data. Indeed, data are a lifeblood of design methodologies and drive current commonly encountered development practices. At the center of the ML methodology lies a default assumption that the data fully represent the problem to be solved (e.g., classification or prediction). We look at the problem and produce a solution through the lens of data; in many cases, this may lead to the data blinding effect. We advocate that a holistic knowledge-data development perspective is urgently needed.
An Informed ML (IML) has emerged as a new direction of research addressing these needs. In brief, IML is sought as a methodology in which data and knowledge are used in unison to design ML systems. From the design perspective encountered in the ML learning environment, data and knowledge are radically different. Data are numeric and precise. Knowledge is general and usually expressed at the higher level of abstraction (generality). Knowledge and data emerge at different levels of information granularity.
In this talk, we deliver a comprehensive taxonomy of main pursuits of IML and link them with key ways the knowledge is represented. A historical perspective is offered by studying the symbolic and subsymbolic processing encountered in successive decades of AI.
The two general categories of physics-oriented and neuro-symbolic constructs associated with the ways in which knowledge and data are explored together. We elaborate on the design process being guided by a prudently augmented additive loss function whose corresponding parts minimize distances between the developed ML model and numeric target values and deliver adherence of the model to information granules reflecting available knowledge. A general taxonomy of neuro-symbolic systems involving: learning-for-reasoning, reasoning-for-learning, reasoning-learning is discussed.
Witold Pedrycz is a Professor and Canada Research Chair (CRC) in Computational Intelligence in
the Department of Electrical and Computer Engineering, University of Alberta, Edmonton, Canada.
He is also with the Systems Research Institute of the Polish Academy of Sciences, Warsaw, Poland.
He also holds an appointment of special professorship in the School of Computer Science,
University of Nottingham, UK. In 2009 Dr. Pedrycz was elected a foreign member of the Polish
Academy of Sciences. In 2012 he was elected a Fellow of the Royal Society of Canada. Witold
Pedrycz has been a member of numerous program committees of IEEE conferences in the area of fuzzy
sets and neurocomputing. In 2007 he received a prestigious Norbert Wiener award from the IEEE
Systems, Man, and Cybernetics Council. He is a recipient of the IEEE Canada Computer Engineering
Medal 2008. In 2009 he has received a Cajastur Prize for Soft Computing from the European Centre
for Soft Computing for “pioneering and multifaceted contributions to Granular Computing”. In 2013
has was awarded a Killam Prize. In the same year he received a Fuzzy Pioneer Award 2013 from the
IEEE Computational Intelligence Society. His main research directions involve Computational
Intelligence, fuzzy modeling and Granular Computing, knowledge discovery and data mining, fuzzy
control, pattern recognition, knowledge-based neural networks, relational computing, and Software
Engineering. He has published numerous papers in this area. He is also an author of 15 research
monographs covering various aspects of Computational Intelligence, data mining, and Software
Engineering. Dr. Pedrycz is intensively involved in editorial activities. He is an Editor-in-Chief
of Information Sciences and Editor-in-Chief of WIREs Data Mining and Knowledge Discovery (Wiley).
He currently serves as an Associate Editor of IEEE Transactions on Fuzzy Systems and is a member
of a number of editorial boards of other international journals.
Tofigh Allahviranloo
Istinye University, Istanbul, Turkey
Tofigh Allahviranloo is a Professor of Applied Mathematics at Istinye University in Istanbul, Türkiye. An accomplished mathematician and computer scientist, Prof. Allahviranloo is dedicated to multi- and interdisciplinary research efforts. His expertise lies primarily in fundamental research in applied fuzzy mathematics, with a special focus on dynamical systems and pioneering applications in applied biological sciences.
Prof. Allahviranloo has made significant scientific contributions, including authoring over 16 international books in English and 10 books in Farsi, as well as approximately 450 publications with renowned publishers such as Elsevier, Springer, Wiley, and Taylor & Francis. He has published more than 250 peer-reviewed journal papers over the past 15 years.
He is the lead editor of the book series, Uncertainty, Computational Techniques and Decision Intelligence, published by ELSEVIER. In addition to his extensive writing activities, Prof. Allahviranloo plays an important role in the academic community as Associate Editor and Editorial Board Member of several prestigious journals. These include Information Sciences opens in new tab/window (ELSEVIER), Fuzzy Sets and Systems (ELSEVIER), Journal of Intelligent and Fuzzy Systems (IOS Press), Iranian Journal of Fuzzy Systems, Mathematical Sciences (Springer), Granular Computing (Springer), Journal of Mathematics and Computer Science (ISRP), and Journal of Computational Methods for Differential Equations (University of Tabriz).
He is currently Executive Editor-in-Chief of Information Sciences, Editor-in-Chief of Transactions on Fuzzy Sets and Systems, Editor-in-Chief of International Journal of Industrial Mathematics, Chairman of International Conference on Decision Sciences (IDS) and Managing Editor of The Journal of Mathematics and Computer Science (International Scientific Research Publications).
In addition, Prof. Allahviranloo is a member of the program committee for the FUZZ-IEEE, NAFIPS Annual Meeting, and IFSA conferences, where he brings his extensive knowledge and experience to these key events in the field of fuzzy systems and applied mathematics.
Ardashir Mohammadzadeh
Sakarya University, Sakarya, Turkey
ABSTRACT : ADVANCEMENT IN TYPE-3 FUZZY SYSTEMS AND CONTROL
This keynote, titled “Advancement in Type-3 Fuzzy Systems and Control,” surveys the rapid evolution of type-3 (T3) fuzzy systems and their growing adoption across a broad range of scientific and technological domains. In recent years, T3 fuzzy frameworks have attracted significant attention due to their enhanced ability to model deep uncertainty, complex nonlinearities, and highly variable operating environments, capabilities increasingly demanded in modern intelligent systems. The talk first reviews the principal methodological advancements in T3 fuzzy systems, highlighting key developments in representation, learning, inference, and computational implementation that have enabled practical deployment. It then introduces Type-3 Adaptive Neuro-Fuzzy Inference Systems (T3-ANFIS) as a unifying learning-and-inference architecture that extends classical ANFIS to higher-order uncertainty modeling. Finally, the keynote presents and critically discusses a recently developed intelligent control scheme based on T3-ANFIS, emphasizing design rationale, validation results, and a real-world implementation to demonstrate feasibility, robustness, and performance in practical control applications.
SHORT BIO ABOUT THE AUTHOR :
Prof. Ardashir Mohammadzadeh is a professor at Sakarya University, Turkey. He also leading a researching team in field of intelligent control systems in China. As reported by Stanford University, in 2021-2024, he was listed among the top 2% of the best researchers in the field of artificial intelligence. He was also listed among the top 1% of highly cited researchers in based on the ESI database. His research interests include control theory, fuzzy logic systems, machine learning, neural networks, intelligent control systems, electric vehicles, power system control systems, chaotic systems, and medical control systems.
Rahib Abiyev
Near East University, North Cyprus, Turkey
Rahib H.Abiyev is a Professor in the Department of Computer Engineering, at Near East University, North Cyprus. In 2001, he founded Applied Artificial Intelligence Research Centre and in 2008, he created “Robotics” research group in Near East University. He is currently chair of Applied Artificial Intelligence Institute and chair of Computer Engineering Department. His current research interests include computational intelligence, fuzzy systems, control systems, and signal processing. He has published set of research papers in related subjects. R.H.Abiyev is listed in the ”World’s 2% Top Scientists” in the field of Artificial Intelligence for 2022, 2023, 2024 and 2025, published by Elsevier BV & Stanford University.
Rustu Burak Eke
The Language and System Foundation, Istanbul, Turkey
Av.Dr. Rüştü Burak Eke graduated from Istanbul University, Faculty of Law in 1982. He received master’s degree (Thesis: "Transfer of Technology through Foreign Investments) and PhD degree (Thesis: Patent Right and License Agreement) at the same university where he worked as a research assistant in the Conflict of Laws Department between 1983-1990 and lecturer at the Faculty of Business Administration between 1990-1995. He was on the board of Başak Insurance Company, an affiliate of state-owned bank Ziraat Bankası between 1995-1996 and thereafter he worked as CEO of Ziraat Leasing, also affiliate of Ziraat Bankası from 1995 to 2003. R. Burak Eke is a member of Istanbul Bar since1985. Currently, he is working as advisor and trainer for numerous companies on the subjects of Communication and Organizational Learning along with his professional activities as an attorney at law. He lectures on contemporary rhetoric at MEF University in Istanbul. He is the founder and trustee of Dil ve Sistem Vakfi (The Language and System Foundation)
Nazim Muzaffarli
Director of the Institute of Economics, Ministry of Science and Education of Azerbaijan (since 2014)
Main books:
- Economic Sketches, 1996
- Azerbaijan's Ranking (in International Comparative Studies), 2006
- Rehabilitation of Post-Conflict Territories of Azerbaijan, 2010
- Social Orientation of the Economy in Right-Wing and Left-Wing Systems, 2014
- Post-Conflict Territories: Economic Potential and Comparative Advantages, 2023
- Government Regulation of Pricing: Cross-Country Analysis and Outcomes for Azerbaijan, 2024
