This course will cover the foundations, techniques and applications of Knowledge Graphs (KGs). The course will start by surveying the state of the art. Then it will focus on advanced topics with a focus on spatio-temporal KGs and their applications in Human-in-the-loop applications. Various case studies will be analyzed which will ecncompass
the integration with IOT sensor streams.
A minimum of 75% attendance is required.
Teaching Methods
This course employs a blended approach of theoretical instruction and practical application to foster a deep understanding of LLMs and prompt engineering. Lectures will introduce key concepts, methods, and ethical considerations, followed by interactive, hands-on exercises designed to reinforce learning through direct experimentation. In-class practical sessions will allow students to engage with real-world LLM use cases, facilitating an applied comprehension of theoretical content.
To promote collaborative learning, students will complete a project assignment in pairs, developing a tailored application or research-oriented task involving LLMs. This project will enable students to deepen their expertise by applying course concepts to a practical problem, encouraging both independent problem-solving and teamwork.
Assessment methods
Assessment for this course will be based on the project work completed in pairs. Students will be required to submit a concise written report detailing their project objectives, approach, and findings. This report will be reviewed for clarity, technical accuracy, and depth of analysis. Following the submission, each pair will participate in a brief oral discussion to present their work and address questions. This dual assessment method will evaluate both the students’ ability to articulate their insights in writing and their competency in discussing technical details, thus ensuring a comprehensive appraisal of their understanding and application of course concepts.
