ITI41222 Evolutionary Computation (Autumn 2023)

The course is connected to the following study programs

Mandatory course in the master programme in applied computer science with specialisation in artificial intelligence, full-time and part-time.

Recommended requirements

Knowledge in:

• Algorithms and data structures
• Programming
• Programming libraries related to machine learning
• Statistics
• Mathematics

Lecture Semester

First semester (autumn) in the full-time and part-time programme.

The student's learning outcomes after completing the course

Knowledge

The student

• understand the basic principles of evolutionary computation.
• gets an overview of different types of evolutionary computation methods
• becomes familiar with the benefits and drawbacks of these methods
• can implement these methods to solve problems in practical, industrial and other complex domains

Skills

The student can

• formulate a real-world problem as an evolutionary search/optimization/classification problem by deciding on necessary representations and evolutionary operators
• decide the suitable evolutionary algorithms/techniques based on the nature of the applications
• implement different evolutionary algorithms/techniques for such problems by using a package and/or coding his/her own algorithms

General competence

The student gains insight into evolutionary, biologically and nature inspired algorithms/techniques for search, optimization, and classification; and becomes capable of working with such algorithms and techniques.

Content

This course gives an insight into different evolutionary computation methods and their applications.

The topics covered in this course are:

• A general overview of the field of evolutionary computation
• The underlying principles and theory of evolutionary computation
• A detailed overview of the leading evolutionary, bio-inspired, social and other nature-inspired algorithms
• Multi-objective evolutionary algorithms
• Hybridization and memetic algorithms
• Neuro-evolution
• Issues with evolutionary computation techniques: parameter control, convergence, diversity, elitism, etc.
• Applications of evolutionary computation methods in solving science, industry and real-world search/optimization/classification tasks
• Advanced and recent trend in evolutionary computation

Forms of teaching and learning

Lectures, colloquium, self-study and project work.

Workload

Approx. 280 hours.

Coursework requirements - conditions for taking the exam

The student must deliver:

• Up to 3 mandatory exercises
• Attend individual oral presentations for each of the announced exercises. During the oral presentations, the student must explain the implementation details of the submission and demonstrate a certain level of efficiency for the submitted solution to the exercise. 

Coursework requirements must be accepted to qualify for the exam.

Examination

Individual portfolio and written exam

The exam is divided into two parts:

• The individual portfolio consists of up to three exercises and determines 50% of the final grade.
• The individual written exam is based on the course curriculum and determines 50% of the final grade. Duration 3 hours. No supporting materials allowed.

Both parts of the exam must be passed to pass the exam as a whole. The student will get an individual joint grade for the entire course. Grades: A - F.

Examiners

External and internal examiner, or two internal examiners.

Conditions for resit/rescheduled exams

Upon re-examination, each part of the examination can be retaken.

Course evaluation

This course is evaluated by a:

• Mid-term evaluation (compulsory)

The responsible for the course compiles a report based on the feedback from the students and his/her own experience with the course. The report is discussed by the study quality committee at the Department of Computer Science and Communication.