Course content

The main focus of the course is to build intelligent systems based on two key natural concepts: the brain, and evolution by natural selection. In computer-science, the analogs for these are artificial neural networks (ANNs) and evolutionary algorithms (EAs). Both methods have thousands of useful applications in fields as diverse as control theory, telecommunications, music and art. This course discusses both methods in great detail along with providing a bit of the biological basis for each.

Learning outcome

Students will get both theoretical and practical programming experience with two of the best known sub-symbolic AI methods: artificial neural networks and evolutionary algorithms.

Learning methods and activities

Regular lectures and homeworks, each lasting 2-4 weeks. The final grade is based 100% upon these homeworks, which normally consist of large programming projects along with essays.

This course is VERY programming intensive and should not be taken by students who dislike writing code.
Group work on programming projects is acceptable, but group size cannot
exceed 2 members. However, any homework that consists solely of a report must be done individually, with no assistance given by one student to another.

Specific conditions

Recommended previous knowledge

TDT4120 Algorithms and Data Structures, TDT4136 Introduction to Artificial Intelligence, TDT4171 Artificial Intelligence Methods, and requires previous knowledge in Discrete Mathematics comparable with MA0301 Elementary Discrete Mathematics.

Required previous knowledge

TDT4136 Introduction to Artificial Intelligence
TDT4171 Artificial Intelligence Methods
The course is only available for students following a specialization in Artificial Intelligence under the programs MTDT, MIDT, MIT, MTIØT.

Course materials

Lecture slides, a textbook (possibly 2). Textbooks are chosen at the beginning of the semester.

Credit reductions