Knowledge Representation

URL study guide

https://studiegids.vu.nl/en/courses/2024-2025/XM_0059

Course Objective

Knowledge and understanding: at the end of the course the students should be acquainted with the broad principles of knowledge representation, such as the separation of representation and reasoning, the declarative nature of representations, the universal (domain independent) nature of inference mechanisms. Apply knowledge and understanding: students will have practical experience with different representation formalisms, and will be able to implement a reasoning tool for at least one of these formalisms. This will allow them to better understand the role of knowledge representation in the broader context of AI. Making judgement: students will be able to set up empirical experiments in order to evaluate the pros and cons of Knowledge Representation formalisms in specific application areas. Communication skills: students will be able to write a scientific report about an original research question in a small group of students. Learning skills: students will be trained in acquiring knowledge about a set of complex formal systems, learn how to come up with a research question and scientific hypotheses, and perform the necessary (empirical) research to prove or disprove those hypotheses.

Course Content

We discuss important formalisms for Knowledge Representation and symbolic AI: Description Logic, Non-montonic reasoning with Default Logics and Argumentation Frameworks, as well as Probabilistic Graphical Models.

Teaching Methods

Lecture: 2 sessions of 2 hours each week, on demand a Q&A session every 2-3 weeks, Working Groups to work on exercises every 2-3 weeks, and two practical assignments, which involve implementation, experimental evaluation and writing a report.

Method of Assessment

-programming assignments in groups (total 50%), -peer reviewing assignment reports (P/F)
- written exam (50%). The peer reviewing assignment report is marked pass/fail only, but must be completed to finish the course (even for resit students). There will be a resit of the written exam, there is no resit opportunity for practical assignments.

Literature

The main source of information for the lecture will be the lecture and the slides
- no additional literature research is mandatory. However, the following literature is recommended: F. van Harmelen, V. Lifschitz, B. Porter: Handbook of Knowledge Representation. Elsevier B.V., 2008. ISBN: 978-0-444-52211-5

Target Audience

Master Artificial Intelligence

Recommended background knowledge

1. Basic knowledge of logic (propositional logic and first-order logic) 2. A good working knowledge of programming in Python is required