Course detail

Applied Evolutionary Algorithms

ÚSI-2IDAAAcad. year: 2015/2016

The course aims to modern optimization techniques and the use of evolutionary algorithms for solution of complex, theoretical and practical problems from engineering practice. In addition, emphasis is also placed on making students familiar with software tools for fast prototyping of evolutionary algorithms.

Language of instruction

Czech

Number of ECTS credits

5

Mode of study

Not applicable.

Learning outcomes of the course unit

Students will obtain special expertise and skills for solution of complex, NP complete problems. A part of skills, that students will acquire, includes: the ability to represent, solve problem for selected evolutionary technique, proper specification of control parameters for optimization process and choosing effective software tools for the implementation of solved problems.

Prerequisites

Basic principles of programming in Java, C programming language, etc.

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Teaching is carried out through lectures that consist of interpretations of basic principles, methodology of given discipline, problems and their exemplary solutions.

Assesment methods and criteria linked to learning outcomes

Students will participate in four, two-hour computer laboratory practices, in which they will solve selected optimization problems. At the end of the semester, students have to hand project which is based upon addressing a theoretical or a practical problem. Knowledge of theoretical and practical principles of evolutionary algorithms is verified by mid-term exam and by the final examination.

Course curriculum

1. Evolutionary algorithms, theoretical foundation, basic distributions (GA, EP,GP, ES).
2. Genetic algorithms (GA), structure, Schemata theory.
3. Genetic algorithms using diploids and messy-chromosomes. Specific crossing.
4. Evolutionary strategy (task parameters, control parameters).
5. Evolutionary programming, Hill climbing algorithm, Simulated annealing.
6. Genetic programming (principles, Symbolic Regression).
7. Advanced estimation distribution algorithms (EDA).
8. Variants of EDA algorithms, UMDA, BMDA and BOA. Bayesian network, network design.
9. Multimodal and multicriterial optimization techniques. Population selection.
10. Dynamic optimization problems.
11. New evolutionary paradigm: immune systems, differential evolution, SOMA.
12. Differential evolution. Particle swarm model.
13. Engineering tasks and evolutionary algorithms.

Work placements

Not applicable.

Aims

The study aim for students is to obtain knowledge and skills for solution of complex optimization problems including mastering software tools for fast prototyping of evolutionary algorithms.

Specification of controlled education, way of implementation and compensation for absences

Not applicable.

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Kvasnička V., Pospíchal J.,Tiňo P.: Evolutionary algorithms. Publisher STU Bratislava, 2000, pp. 215, ISBN 80-227-1377-5.

Recommended reading

Back, J.: Evolutionary algorithms, theory and practice, New York, 1996, ISBN:0-19-509971-0.

Classification of course in study plans

  • Programme MRzI Master's

    branch RIS , 2 year of study, summer semester, compulsory-optional

Type of course unit

 

Lecture

26 hod., optionally

Teacher / Lecturer

Exercise

26 hod., optionally

Teacher / Lecturer