Course detail

Evolutionary Computation

FIT-EVDAcad. year: 2020/2021

Evolutionary computation in the context of artificial intelligence and hard optimization problems. Single- and multi-objective optimization, dominance relation, Pareto front. Principles of genetic algorithms, evolutionary strategy, genetic programming and other evolutionary heuristics. Statistical evaluation, theoretical analysis of evolutionary algorithms. Advanced evolutionary algorithms based on probabilistic models. Parallel evolutionary algorithms. Multi-objective evolutionary algorithms. Rapid prototyping of evolutionary algorithms.


Doctoral state exam - topics:

  1. Problem encoding, genotype, phenotype, fitness function.
  2. Genetic algorithms, schema theory.
  3. Evolution strategies.
  4. Genetic programming and symbolic regression.
  5. Estimation distribution algorithms.
  6. Simulated annealing
  7. Multi-objective evolutionary optimization.
  8. Parallel evolutionary algorithms.
  9. Differential evolution, SOMA.
  10. Statistical analysis of experiments.

Learning outcomes of the course unit

Skills and approaches required for solving hard optimization problems using evolutionary algorithms.
Deeper understanding of the optimization problem and its solution in computer engineering.

Prerequisites

Not applicable.

Co-requisites

Not applicable.

Recommended optional programme components

Not applicable.

Recommended or required reading

Eiben, A.E., Smith, J.E.: Introduction to Evolutionary Computing. 2nd ed. Springer, 2015, ISBN 978-3-662-44873-1.
Brabazon, A., O'Neill, M., McGarraghy, S.: Natural Computing Algorithms. Springer, 2015, ISBN 978-3-662-43630-1.
Bentley, P.: Evolutionary Design by Computers. Morgan Kaufmann, 1999, ISBN 978-1558606050.
Doerr, B. Neumann F. (eds.): Theory of Evolutionary Computation. Springer, 2020, ISBN 978-3-030-29413-7

Planned learning activities and teaching methods

Not applicable.

Assesment methods and criteria linked to learning outcomes

Submission of the project on time, exam.

Language of instruction

Czech, English

Work placements

Not applicable.

Aims

To acquaint students with modern evolutionary algorithms developed for solving hard optimization and design problems.

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

During the course, it is necessary to submit the project and pass the exam. Teaching is performed as lectures or controlled self-study; the missed classes need to be replaced by self-study.

Classification of course in study plans

  • Programme VTI-DR-4 Doctoral

    branch DVI4 , any year of study, summer semester, 0 credits, elective

  • Programme VTI-DR-4 Doctoral

    branch DVI4 , any year of study, summer semester, 0 credits, elective

Type of course unit

 

Lecture

26 hours, optionally

Teacher / Lecturer

Syllabus

  1. Introduction to evolutionary computation.
  2. Genetic algorithms, schema theory.
  3. Statistical analysis of experiments.
  4. Typical optimization problems.
  5. Advanced techniques in genetic algorithms.
  6. Theoretical analysis of evolutionary algorithms.
  7. Multi-objective evolutionary optimization.
  8. Evolution strategies.
  9. Genetic programming and symbolic regression.
  10. Parallel evolutionary algorithms.
  11. Estimation distribution algorithms.
  12. Simulated annealing, differential evolution, SOMA and other relevant algorithms.
  13. Recent trends.

Guided consultation in combined form of studies

26 hours, optionally

Teacher / Lecturer