Course detail

Information Representation and Machine Learning

FEKT-DPA-IMLAcad. year: 2021/2022

Complexity theory, genetic algorithms, genetic programming, graph theory, graph equivalence, inforamtion representation, neural networks, reinforcement learning, embeddings. 

Language of instruction

English

Number of ECTS credits

4

Mode of study

Not applicable.

Offered to foreign students

The home faculty only

Learning outcomes of the course unit

Not applicable.

Prerequisites

Not applicable.

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Not applicable.

Assesment methods and criteria linked to learning outcomes

final examination

Course curriculum

1. Information representation, introduction
2. Complexity theory, selected examples of complexity
3. Graph theory, analysis, factorization
4. Theory of graphs, groups, availability, bipartite
5. Graphs equivalence
6. Information representation - machine learning
7. Information representation - network types
8. Information representation - linear regression
9. Information representation - logistic regression, classification
10. Information representation - feed forward neural network
11, Information representation - recurrent neural network
12. Information representation - reinforcement learning
13. Information representation - NN with graphs and trees

 

Work placements

Not applicable.

Aims

Objective of this course is to provide information about complexity theeory, graph theory and their comparison, queuing theory, Petri nets, evolution 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

Goldreich, Oded. "Computational complexity: a conceptual perspective." ACM SIGACT News 39.3 (2008): 35-39. (EN)

Recommended reading

Mitleton-Kelly, Eve. Complex systems and evolutionary perspectives on organisations: the application of complexity theory to organisations. Elsevier Science Ltd, 2003. (EN)
Bürgisser, Peter, Michael Clausen, and Amin Shokrollahi. Algebraic complexity theory. Vol. 315. Springer Science & Business Media, 2013. (EN)

eLearning

Classification of course in study plans

  • Programme DPA-EIT Doctoral, any year of study, summer semester, compulsory
  • Programme DKA-EIT Doctoral, any year of study, summer semester, compulsory
  • Programme DPAD-EIT Doctoral, any year of study, summer semester, compulsory

Type of course unit

 

Seminar

39 hours, optionally

Teacher / Lecturer

eLearning