Artificial Intelligence, 7.5 Credits

Contents

This course gives an introduction to the fundamentals of Artificial Intelligence (AI) including robotics and natural language processing, exploring both the historical roots and the latest applications. You will learn how to implement and apply classical AI algorithms for knowledge representation, planning, searching, and game-playing. The course focuses on symbolic artificial intelligence with techniques based on discrete mathematics and logics. Non-symbolic approaches common in machine learning and deep learning are briefly introduced and discussed in relation to symbolic AI.

Module 1, theory, 4.5 credits. The module introduces classical AI. It covers some historical background, fundamental problems, and modern-day applications. The course discusses problems such as the frame problem, the Turing test, the Chinese room argument, and various problem-solving techniques, including heuristic search algorithms and AI in games.

Additionally, the module addresses AI paradigms such as knowledge representation, logic programming, and robotics with an emphasis on sensors and actuators. It covers different agent paradigms, classical planning methods, and machine learning algorithms such as k-NN and deep learning.

The module also explores natural language processing (NLP), Large Language Models (LLMs), and Explainable AI. Ethical considerations and responsible AI use are emphasized, addressing biases and ensuring transparency and accountability.

Module 2, practice, 3 credits. In this module, some of the theories, methods, and concepts treated in the theory module are put into practice.

Expected learning outcomes

Knowledge and understanding
After completing the course, the student should be able to:

• (FSR 1) Discuss the fundamental issues and challenges in AI.
• (FSR 2) Explain algorithms for informed and adversarial search as well as search heuristics and related concepts.
• (FSR 3) Compare and contrast methods and theories for reactive robots and robot architectures.
• (FSR 4) Explain the underlying principles of common actuators and sensors, along with techniques for sensor fusion.
• (FSR 5) Explain fundamental approaches to machine learning and explainable AI.
• (FSR 6) Exemplify fundamental methods for Natural Language Processing (NLP).

Competence and skills
After completing the course, the student should be able to:

• (FSR 7) Apply formal logical methods for knowledge representation and planning.
• (FSR 8) Implement efficient AI algorithms (e.g., algorithms for clustering, artificial neural networks, path tracking, game search) and empirically evaluate their performance.
• (FSR 9) Solve problems by identifying and applying appropriate AI methods.

Judgement and approach
After completing the course, the student should be able to:

• (FSR 10) Discuss the responsible use of AI technologies in society.
• (FSR 11) Assess to what extent the latest advances in AI overcome the fundamental limitations of AI.

Required Knowledge

At least 60 ECTS within Computing Science. At least 15 ECTS programming; 7.5 ECTS data structures and algorithms; 7.5 ECTS discrete mathematics; and 7.5 ECTS logics. Students enrolled on the master's program in artificial intelligence (TAAIM) are eligible.

Form of instruction

Instruction consists of lectures and computer-based assignments. In addition to scheduled activities, individual work with the material is required.

Examination modes

The assessment of Module 1 (FSR 1-7) is done by a written exam in halls. The grade scale on the module is Fail (U), Pass (G), or Pass with Distinction (VG).

The assessment of Module 2 (FSR 8-11) is done by assignments presented orally and in writing as well as seminars. The grade scale on the module is Fail (U) or Pass (G).

On the course as a whole, the grades given are Fail (U), Pass (G), or Pass with Distinction (VG). When both modules have been completed, the grade on the course as a whole will be the same as the grade on Module 1.

Adapted examination
The examiner can decide to deviate from the specified forms of examination. Individual adaptation of the examination shall be considered based on the needs of the student. The examination is adapted within the constraints of the expected learning outcomes. A student that needs adapted examination shall no later than 10 days before the examination request adaptation from the Department of Computing Science. The examiner makes a decision of adapted examination and the student is notified.

Other regulations

The course cannot be included in a degree together with the course 5DV124 or 5DV201.

If the syllabus has expired or the course has been discontinued, a student who at some point registered for the course is guaranteed at least three examinations (including the regular examination) according to this syllabus for a maximum period of two years from the syllabus expiring or the course being discontinued.