The presentation explores the intersection of neurosymbolic artificial intelligence (AI), Retrieval-Augmented Generation (RAG), and Knowledge Graphs. Neurosymbolic AI combines the strengths of neural networks with symbolic reasoning and RAG enhances AI capabilities by augmenting generative models with external knowledge retrieval, improving accuracy and contextual understanding. When integrated with knowledge graphs—structured representations of domain-specific knowledge—RAG systems can dynamically access and leverage vast, interconnected datasets. This combination fosters more sophisticated, context-aware systems capable of reasoning, inferring, and generating human-like responses across a range of complex tasks. The talk will delve into the technical synergies of these approaches and their implications for the future of AI.
Dr. Sotirios Batsakis is Assistant Professor at the Hellenic Mediterranean University specializing on Artificial Intelligence, Knowledge Representation, Internet Information Retrieval and the Semantic Web. He received a diploma on Computer Engineering and Informatics from the Computer Engineering and Informatics Department, School of Engineering, University of Patras with highest distinction (2000), then obtained an MSc with highest distinction (2008) and a PhD from the ECE School of the Technical University of Crete (2012) were he has also worked as post-doctoral researcher and laboratory teaching staff and before that as a computer engineer and instructor in the public and private sector. He has also worked as Senior Researcher and Senior Lecturer at the University of Huddersfield, UK. He has participated in numerous research projects and received multiple Marie Curie fellowships focusing on the broader field of Artificial Intelligence. Results of the above-mentioned research activities and collaborations are more than 60 publications in international scientific journals and conferences, including top conferences such as SSTD, ICLP, ESWC, ISWC, and AAAI.
