At the end of the course, the student will:

 

1. Know and understand the techniques in the different fields of AI, such as machine learning, symbolic reasoning, cognitive science and computational linguistics.
2. Be able to choose from and use different research methods in AI. More specifically, you will be able to:
   1. Implement different AI techniques in a working programme;
   2. Test and evaluate an AI system (technical capabilities, performance, usability);
   3. Write a technical report and a research paper on an AI system, its evaluation and its place in the broader context of AI

Grading

The final grade for the course is composed as follows:

• 30% project part 1 - designing and implementing a state-based dialog system that uses machine learning (learning objective 2a and 2c).
• 30% project part 2 - designing and carrying out an experiment to evaluate your dialog system, and writing a research paper to discuss your evaluation and place your system in a wider context (learning objective 2b and 2c).
• 40% individual final exam with theory-questions about techniques in AI. The exam will consist of questions that relate to the lectures and associated literature (learning objective 1).

To pass the course all three individual grades need to be at least 5.0 unrounded. Moreover, the weighted final grade needs to be at least 5.5 unrounded.

The repair test requires at least a 4 for the original test.

Artificial Intelligence is a fast-paced and challenging field that is making visible inroads into our everyday life. AI in Utrecht offers a unique interdisciplinary approach, integrating the areas of computer science and agent systems, cognition and psychology, logic and philosophy, and linguistics. Because of this interdisciplinary character, the variety of techniques and methods used is considerable, ranging from theoretical to empirical, and from formal mathematical to more informal philosophical. 

 
In this course, we will introduce the various perspectives on AI in Utrecht and the methods associated with them. We will look at the basics of machine learning, logic and symbolic reasoning, cognitive science and computational linguistics, and discuss the part they play in modern AI systems.

We will further discuss important methods commonly used in AI research: knowledge modelling, system engineering, and empirical evaluation of machine learning and human-computer interaction. We further practice general academic skills such as reviewing literature, working in teams and scientific writing.

The linking pin of the course is a central lab project in which you will develop, describe, test, and evaluate a dialog system (sometimes also referred to as “chatbot”). In this way, the theory from the lectures forms the basis of a real AI application that you will evaluate with users.  

Form
Lectures and lab sessions.

Literature
See Blackboard page of the course.