Evolution from Semantic Web to Semantic AI. Knowledge representation paradigms. Resource Description Framework (RDF) and RDF*, RDF Schema (RDFS), Web Ontology Language (OWL), and Description Logics. Ontology engineering methodologies, ontology design patterns, ontology development tools, and semantic reasoning. SPARQL query language and semantic interoperability through Linked Open Data.
From ontologies to knowledge graphs. Knowledge graph fundamentals and architecture. Triple stores and graph databases. Knowledge graph construction: information extraction, entity recognition, entity linking, relation extraction, and knowledge graph population. Semantic search, knowledge graph embeddings, vector databases, enterprise knowledge graphs, and applications in healthcare, agriculture, Industry 4.0, smart cities, and scientific knowledge management.
Introduction to Large Language Models (LLMs) and limitations of standalone LLMs. Knowledge-augmented LLMs, Retrieval-Augmented Generation (RAG), Graph RAG, and LLM–Knowledge Graph integration. Neuro-symbolic AI, semantic agents, explainable AI using knowledge graphs, trustworthy AI, and future directions in Semantic AI.