TUTORIALS
Presenter: Dr. Dionisios N. Sotiropoulos
Title: Navigating the Nexus: Leveraging Deep Learning for Social Network Analysis
Abstract: In this tutorial, we explore the sophisticated realm where deep learning meets social network analysis, highlighting how state-of-the-art algorithms such as Long Short-Term Memory networks (LSTMs), Transformers, BERT, Graph Neural Networks, and Convolutional Neural Networks are transforming our understanding of complex online social structures. As digital platforms burgeon with vast amounts of textual and relational data, developing robust analytical tools to parse and understand this information is increasingly vital. This session will delve into the application of these advanced deep learning models to dissect both the structural frameworks and the rich text content of online social networks, shedding light on user behavior, community dynamics, and emerging trends. Through practical demonstrations and case studies, participants will gain firsthand experience in applying these technologies to real-world challenges, thereby enhancing their analytical capabilities and opening up new avenues for research and discovery in digital social interactions.
Bio: Dr. Dionisios N. Sotiropoulos is currently an Assistant Professor (tenured) in the Department of Informatics of the University of Piraeus, Greece. He received his PhD. in Computer Science from the Department of Informatics at the University of Piraeus, Greece in 2011 as well as a B. Sc. in Informatics in 2003. He has worked as a post-doctoral researcher in the Department of Management Science and Technology at Athens University of Economics and Business, as a member of the SocioMine group. He has also been a visiting researcher at Norwich Business School, University of East Anglia. His primary research interests are in the areas of machine learning, data mining, evolutionary computing and signal processing, and applications in user modeling, information retrieval and intelligent software systems. His interest in Digital Social Media focuses on the development of bio-inspired machine learning algorithms for data mining purposes within the context of digital social networks.
Presenter: Dr. Konstantina Ch. Chrysafiadi
Title: Incorporating fuzzy logic in intelligent software systems
Abstract: Artificial Intelligence-empowered software systems are continually evolving, with fuzzy logic frequently serving as a fundamental enabling technology. This tutorial aims to provide a comprehensive understanding of how fuzzy logic can enhance the capabilities of intelligent systems, enabling them to handle uncertainty, imprecision, and approximate reasoning more effectively. We will explore the foundational concepts of fuzzy logic, including fuzzy sets, membership functions, linguistic variables and fuzzy inference systems. Also, we will discuss other Artificial Intelligence techniques, which are often combined with fuzzy logic. Emphasis will be placed on the advantages of fuzzy logic in improving system adaptability, robustness, and human-like reasoning. Furthermore, through practical applications and case studies, attendees will have the opportunity to delve into the implementation of fuzzy logic into various software systems, enhancing their intelligence and performance.
Bio: Dr. Konstantina Chrysafiadi is currently an Assistant Professor in the Department of Informatics of the University of Piraeus, Greece. Previously, she worked as Laboratory Teaching Staff in the same Department for 6 years. She received her postdoctoral and Phd in Computer Science from the Department of Informatics of the University of Piraeus, a M.Sc. degree in Information Systems from the Athens University of Economics and Business, and an B. Sc. in Computer Science from the Department of Informatics of the University of Piraeus. She teaches courses in both undergraduate and graduate degree programs. She has also supervised the graduation theses of undergraduate and graduate students. She is the author of two monographs, several chapters in books, as well as a significant number of articles published in international peer-reviewed journals and papers presented at international conferences. She received the “Best Paper Award” at the 11th International Conference on Information, Intelligence, Systems and Applications (IISA 2020). Her research interests include Artificial Intelligence, Fuzzy Logic–based systems, Knowledge-based systems, adaptive systems, user modeling and distance learning.
Presenter: Dr. Dimitrios P. Panagoulias
Title: Evaluating Multimodal Large Language Models: Benchmarks, Methods, and Analytical Approaches.
Abstract: Large language models (LLMs) constitute a breakthrough in state-of-the-art Artificial Intelligence technology, which is rapidly evolving and being utilized in various domains. Applications augmented by LLMs can generate and edit images, create text based on specific prompts or assigned tasks, and extract and discuss features of images. However, given the vast amount of training data used to engineer and fine-tune these models, the output can often be misleading and baseless, a process known as hallucination. In this tutorial, the architecture of these models will be analyzed comprehensively. Evaluation paradigms and analytical tools for measuring the performance and domain-specific capacity of LLMs will be presented via a series of use cases, utilizing and showcasing tools for Image-Metadata-Analysis, Named-Entity-Recognition, Knowledge-Graphs, and Multi-Genre Natural Language Inference
Bio: Dimitrios P. Panagoulias holds a Bachelor’s Degree in Business Administration from the Athens University of Economics and Business, Greece, and a M.B.A., a M.Sc. in Computer Science and a Ph.D. in Artificial Intelligence-empowered Biomedical Applications, from the University of Piraeus, Greece. He has authored or co-authored numerous publications in international journals, book chapters, and conference proceedings. Since 2011, he has been at the helm of Dermacen S.A., a secondary healthcare provider in Greece specializing in dermatology, venereology, and plastic surgery. In 2018, he established Disk Inside I.T. Development and Consulting Ltd in the U.K., a company focusing on developing CRM and ERP software and LLM agents, mainly for the medical sector, and providing consultation related to digital transformation and branding. His research focuses on machine learning and pattern recognition, the development of AI-infused systems and APIs using iterative or agile development methodologies, and functional and object-oriented programming with .NET, Python, and JavaScript.