About this course
Evolutionary algorithms are population-based, stochastic search algorithms based on the mechanisms of natural evolution.
This course covers how to design representations and variation operators for specific problems.
Furthermore convergence behavior and population sizing are analyzed.
The course focuses on the combination of evolutionary algorithms with local search heuristics to solve combinatorial optimization problems like graph bi-partitioning, graph coloring, and bin packing.
Course form
Lectures, lab sessions.
Study material
To be announced.
Learning outcomes
After completing the course, students have
- a thorough knowledge of the concepts, techniques, analyses, and algorithms in the field of evolutionary computation and meta-heuristic search algorithms.
- theoretical knowledge to understand the behavior of evolutionary and meta-heuristic search algorithms.
- a thorough knowledge of state-of-the-art applications of evolutionary computation and meta-heuristic search algorithms.
- a thorough knowledge of solving multi-objective optimization problems with metaheuristic search algorithms.
and are capable of
- designing efficient and high performance meta-heuristic search problem for diverse discrete optimization problems.
- reading and understanding key journal publications in the field of evolutionary computation and meta-heuristic search algorithms.
- experimentally comparing different meta-heuristic search algorithms on a set of benchmark problems.
- implementing meta-heuristic search algorithms to solve hard, discrete optimization problems.
- analyzing the performance and sensitivity of meta-heuristic search algorithms.
- performing a statistically sound analysis of the experimental results of different meta-heuristic search algorithms.
- working together with other students on designing, building, and testing evolutionary and meta-heuristic search algorithms.
- making English language presentations in writing of one’s own research.
- making English language presentations orally of one’s own research.
Assessment
The assessment consists of
- a written exam (50% of the final mark)
- lab assignments (40%)
- paper report (10%).
To qualify for a repair of the final result the mark needs to be at least a 4.
Prior knowledge
You must meet the following requirements
- Assigned study entrance permit for the master
Resources
Additional information
- More infoCoursepage on website of Utrecht University
- Contact a coordinator
- CreditsECTS 7.5
- Levelmaster
Offering(s)
Start date
3 February 2025
- Ends11 April 2025
- Term *Period 3
- LocationUtrecht
- Instruction languageEnglish
Enrolment starts in 57 days