Invited Speakers

Irina Perfilieva

Title: Feedforward Neural Networks: Interpretability in the Hands of Mathematics

Bio: Professor Irina Perfilieva, Ph.D., received the degrees of M.S. (1975) and Ph.D (1980) in Applied Mathematics from the Lomonosov State University in Moscow, Russia. She is Professor Honoris Causa in Amity Institute of Information Technology, Noida, India, and Doctor Honoris Causa in the University of Latvia, Latvia. At present, she is full professor of Applied Mathematics in the University of Ostrava, Czech Republic.

She is the author and co-author of six books on mathematical principles of fuzzy sets and fuzzy logic, the co-editor of one book and many special issues of scientific journals. She has published over 270 papers in the area of multi-valued logic, fuzzy logic, fuzzy approximation and fuzzy relation equations. She is an area editor of Soft Computing, member of editorial boards of the following journals: Fuzzy Sets and Systems, IEEE Transactions on Fuzzy Systems, Journal of Computational Intelligence Research, Iranian Journal of Fuzzy Systems. She works as a member of Program Committees of the most prestigious International Conferences and Congresses in the area of fuzzy and knowledge-based systems.

For her many years of scientific achievements, she has received several awards, including an IFSA fellow and an honorary member of EUSFLAT. She received the 1st memorial Da Ruan award in 2012. She has two patents in the area of time series processing and the Internet service technique. 

Her scientific interests lie in the area of fuzzy and mathematical modeling based on rigorous functional analysis and sophisticated numerical methods. She is the author of the generally accepted method of fuzzy transforms, successfully used in image and time series processing, numerical analysis and methods to solve differential and differential-integral equations, including fractional ones and those over fuzzy-valued functions.

Her recent interests are in the area of data analysis and the mathematical foundation of neural networks.  She successfully uses modern as well as classical approaches.

Vilem Novak

Title: Non-monotonic Commonsense Reasoning with Intermediate Quantifiers

Abstract:

Intermediate quantifiers are natural language expressions using which we quantify the number of specimens in various contexts. Typical examples of them are “Many, most, a lot of, a few, several, almost all”, and other similar expressions. In this talk we will present results obtained in formal theory of their semantics. Furthermore, we will focus on reasoning using generalised syllogisms in which these quantifiers occur. We will demonstrate how validity of syllogisms can be proved and show various examples of them. We will also present generalised square of opposition and show how it is related to non-monotonic reasoning and how the latter is included in our theory. Among others, we will show that the classical example “Most birds fly” and “Tweety is a penguin which does not fly” does not lead to contradiction in our theory. We will also briefly mention the concept of Fuzzy Natural Logic (FNL) that is a system of theories of mathematical fuzzy logic enabling us to model special cases of human reasoning that is based on the use of natural language. FNL stems from the results of classical linguistics, logical analysis of concepts and semantics of natural language, and higher-order mathematical fuzzy logic. We will show that FNL is a bridge to formalization of commonsense knowledge and commonsense reasoning. We will give arguments that vagueness is inherent, non-removable constituent of linguistic meaning and plays important role in problems of AI where natural language is employed.

Bio: Prof. Vilém Novák, Ph.D., DSc. is the founder and former director of the Institute for Research and Applications of Fuzzy Modeling of the University of Ostrava, Czech Republic. The institute (established in 1996) is one of the world-renowned scientific workplaces that significantly contributed to the theory and applications of fuzzy modeling. V. Novák obtained a PhD in mathematical logic at Charles University, Prague in 1988; DSc. (Doctor of Sciences) in computer science in the Polish Academy of Sciences, Warsaw in 1995; full professor at Masaryk University, Brno in 2001. His research activities include mathematical fuzzy logic, approximate reasoning, mathematical modeling of linguistic semantics, fuzzy control, analysis and forecasting of time series, and various kinds of fuzzy modeling applications. He belongs among the pioneers of the fuzzy set theory. He was general chair of the VIIth IFSA’97 World Congress, Prague and of the international conferences EUSFLAT 2007, Ostrava and EUSFLAT 2019, Prague. He is a member of the editorial boards of several scientific journals. He is often invited to give plenary talks at international conferences and give lectures in universities worldwide. He is the author or co-author of 6 scientific monographs, two edited monographs, and over 310 scientific papers with almost 9000 citations. He was awarded in the International Conference FLINS 2010 in China and obtained the title “IFSA fellow” in 2017 for his scientific achievements. He is currently the vice-president of IFSA.

Anoop Sathyan – NAFIPS 2023 Early Carreer Award Recipient

Title: Machine learning for cooperative robotics and healthcare

Abstract: Machine learning methods are being used for a wide variety of applications. This talk will mainly focus on the use of Genetic fuzzy systems (GFS) for cooperative reinforcement learning. This includes the design of a scalable framework of GFS which has been used in cooperative robotics where a team of homogenous, decentralized robots work together to accomplish a common goal. This framework provides the capability to add or remove robots from the team without requiring additional training. Further, this framework has been extended to large-scale problems involving autonomous vehicles for cooperative merge and platooning to maintain smooth flow of traffic. The talk will include other ML methods that have been used in the healthcare domain.

Bio: Dr. Anoop Sathyan is currently working as a Senior Research Associate in the Department of Aerospace Engineering at University of Cincinnati. He is also a co-lead of AI-Bio Lab at UC where he is involved in the design and development of machine learning tools for various applications such as cooperative robotics, autonomous transportation and healthcare. His research interests include genetic fuzzy, neural networks, reinforcement learning, anomaly detection, control systems and optimization.