Course detail

Soft Computing

FIT-SFCAcad. year: 2011/2012

Soft computing covers non-traditional technologies or approaches for solving hard real-world problems. Content of course, in accordance with meaning of its name, is as follow: Tolerance of imprecision and uncertainty as the main attributes of soft computing theories. Neural networks. Fuzzy logic. Genetic algorithms. Probabilistic reasoning. Rough sets. Chaos.  Hybrid approaches (combinations of neural networks, fuzzy logic and genetic algorithms).

Language of instruction

Czech

Number of ECTS credits

5

Mode of study

Not applicable.

Guarantor

doc. Ing. František Zbořil, CSc.

Department

Department of Intelligent Systems (UITS)

Learning outcomes of the course unit

Students acquire knowledge of soft computing theories fundamentals and so they will be able to design program systems using approaches of these theories for solving various real-world problems.

Students awake the importance of tolerance of imprecision and uncertainty for design of robust and low-cost intelligent machines.

Prerequisites

There are no prerequisites

Co-requisites

Not applicable.

Planned learning activities and teaching methods

Not applicable.

Assesment methods and criteria linked to learning outcomes

Výuka není kontrolována.

Course curriculum

  1. Introduction, Soft Computing concept explanation. Importance of tolerance of imprecision and uncertainty.
  2. Biological and artificial neuron, neural networks. Adaline, Perceptron. Madaline and BP (Back Propagation) neural networks.
  3. Adaptive feedforward multilayer networks.
  4. RBF and RCE neural networks. Topologic organized neural networks, competitive learning, Kohonen maps.
  5. CPN , LVQ, ART.
  6. Neural networks as associative memories (Hopfield, BAM, SDM).
  7. Solving optimization problems using neural networks. Stochastic neural networks, Boltzmann machine.
  8. Fuzzy sets, fuzzy logic and fuzzy inference.
  9. Genetic algorithms.
  10. Probabilistic reasoning.
  11. Rough sets.
  12. Chaos.
  13. Hybrid approaches (neural networks, fuzzy logic, genetic algorithms sets).

Work placements

Not applicable.

Aims

To give students knowledge of soft computing theories fundamentals, i.e. of fundamentals of non-traditional technologies and approaches to solving hard real-world problems, namely of fundamentals of artificial neural networks, fuzzy sets and fuzzy logic and genetic algorithms.

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

  1. Mid-term written test
  2. Individual project

Recommended optional programme components

Not applicable.

Prerequisites and corequisites

Not applicable.

Basic literature

Kriesel, D.: A Brief Introduction to Neural Networks, 2005, Fundamentals of the New Artificial Intelligence, Springer-Verlag New York, Inc., 2008. ISBN 978-1-84628-838-8 
Rutkowski, L.: Flexible Neuro-Fuzzy Systems, Kluwer Academic Publishers, 2004, ISBN 1-4020-8042-5
Russel,S., Norvig,P.: Artificial Intelligence, Prentice-Hall, Inc., third edition 2010, ISBN 0-13-604259-7

Recommended literature

Mehrotra, K., Mohan, C. K., Ranka, S.: Elements of Artificial Neural Networks, The MIT Press, 1997, ISBN 0-262-13328-8 Munakata, T.: Fundamentals of the New Artificial Intelligence, Springer-Verlag New York, Inc., 2008. ISBN 978-1-84628-838-8 Russel, S., Norvig, P.: Artificial Intelligence, Prentice-Hall, Inc., 1995, ISBN 0-13-360124-2, second edition 2003, ISBN 0-13-080302-2, third edition 2010, ISBN 0-13-604259-7

Type of course unit

 

Lecture

26 hod., optionally

Teacher / Lecturer

doc. Ing. František Zbořil, CSc.

Syllabus

  1. Introduction, Soft Computing concept explanation. Importance of tolerance of imprecision and uncertainty.
  2. Biological and artificial neuron, neural networks. Adaline, Perceptron. Madaline and BP (Back Propagation) neural networks.
  3. Adaptive feedforward multilayer networks.
  4. RBF and RCE neural networks. Topologic organized neural networks, competitive learning, Kohonen maps.
  5. CPN , LVQ, ART.
  6. Neural networks as associative memories (Hopfield, BAM, SDM).
  7. Solving optimization problems using neural networks. Stochastic neural networks, Boltzmann machine.
  8. Fuzzy sets, fuzzy logic and fuzzy inference.
  9. Genetic algorithms.
  10. Probabilistic reasoning.
  11. Rough sets.
  12. Chaos.
  13. Hybrid approaches (neural networks, fuzzy logic, genetic algorithms sets).

Project

26 hod., optionally

Teacher / Lecturer

doc. Ing. František Zbořil, CSc.