Artificial Intelligence is a broad topic and has emerged as an increasingly powerful subject within the field of computer science. Today, AI applications are embedded in many products and solutions in a plethora of applications ranging from traditional industry, medical diagnosis, speech recognition, robotics, web search and so much more.
This course is designed as the first graduate course, and it introduces the basic concepts by focusing on an intuitive understanding, an algorithmic and mathematical perspective. The course starts by providing an overview of what the latest generation of Artificial Intelligence techniques can achieve. Then it covers the most important concepts and techniques. For each of these techniques, the course will illustrate both the potential and current limitations. We also spend some time on machine learning methods. For all these techniques we provide an introspection into the mathematical foundations and concepts behind them. Through the use of exercises, and a programming project, students get the opportunity to further apply in their knowledge in a practical moments.
Course type:
- AI track: elective
- AS track: elective
- Joint curriculum: foundational
Time: Given yearly, Spring
Teachers: Amy Loutfi (OrU), Dave Zachariah (UU)
Examiner: Amy Loutfi (OrU)
The course requires solid programming experience in a high-level language; the programming assignments will use Python. No previous knowledge of Artificial Intelligence is required. The participants are assumed to have a background in mathematics and logic corresponding to the contents of the WASP-courses “Mathematics for ML” and “Introduction to logic for AI”.
Artificial Intelligence is a broad topic and today’s AI is based on both learning and inference. In this course we will focus on the foundational topics within artificial intelligence.
This course is designed as the first graduate course, and it introduces the basic concepts by focusing on an intuitive understanding as well as an algorithmic and mathematical perspective.
On completion of the course the students should be able to
- explain and analyse foundational techniques in AI and machine learning
- propose, evaluate, and implement solutions to problems requiring AI and machine learning techniques
- gain an understanding in how and where AI and machine learning can be applied in solving problems
The course covers the following topics:
- Problem solving by search
- Intelligent agents
- Logic and inferences
- Automated planning
- The machine learning problem
- Supervised learning
- Support vector machines, regressions
- Kernel methods
- Probabilistic modeling, including the Gaussian process
- Deep learning
- Approximate methods, variational inference
- Unsupervised learning
Obligatory
- Russell & Norvig – Artificial Intelligence, Modern Approach (latest edition)
- Lecture notes to give a mathematical background and outlookto Russell & Norvig
Recommended
Examination format: obligatory exercises.
Syllabus (Kursplan)
Course page
If you are not a student at KTH you must login via https://canvas.kth.se/login/canvas