Course detail
Soft Computing
FITSFCAcad. year: 2018/2019
Soft computing covers nontraditional technologies or approaches to solving hard realworld 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. Nature inspired optimization algorithms. Probabilistic reasoning. Rough sets. Chaos. Hybrid approaches (combinations of neural networks, fuzzy logic and genetic algorithms).
Supervisor
Department
Learning outcomes of the course unit
 Students will acquaint with basic types of neural networks and with their applications.
 Students will acquaint with fundamentals of theory of fuzzy sets and fuzzy logic including design of fuzzy controller.
 Students will acquaint with natureinspired optimization algorithms.
 Students will acquaint with fundamentals of probability reasoning theory.
 Students will acquaint with fundamentals of rouhg sets theory and with use of these sets for data mining.
 Students will acquaint with fundamentals of chaos theory.

Students will learn terminology in Softcomputing field both in Czech and in English languages.
 Students awake the importance of tolerance of imprecision and uncertainty for design of robust and lowcost intelligent machines.
Prerequisites
 Programming in C++ or Java languages.
 Basic knowledge of differential calculus and probability theory.
Corequisites
Not applicable.
Recommended optional programme components
Not applicable.
Recommended or required reading
 Mehrotra, K., Mohan, C. K., Ranka, S.: Elements of Artificial Neural Networks, The MIT Press, 1997, ISBN 0262133288
 Munakata, T.: Fundamentals of the New Artificial Intelligence, SpringerVerlag New York, Inc., 2008. ISBN 9781846288388
 Russel, S., Norvig, P.: Artificial Intelligence, PrenticeHall, Inc., 1995, ISBN 0133601242, second edition 2003, ISBN 0130803022, third edition 2010, ISBN 0136042597
 Aliev,R.A, Aliev,R.R.: Soft Computing and its Application, World Scientific Publishing Co. Pte. Ltd., 2001, ISBN 9810247001
 Mehrotra, K., Mohan, C., K., Ranka, S.: Elements of Artificial Neural Networks, The MIT Press, 1997, ISBN 0262133288
 Munakata, T.: Fundamentals of the New Artificial Intelligence, SpringerVerlag New York, Inc., 2008. ISBN 9781846288388
 Rutkowski, L.: Flexible NeuroFuzzy Systems, Kluwer Academic Publishers, 2004, ISBN 1402080425
 Russel,S., Norvig,P.: Artificial Intelligence, PrenticeHall, Inc., 1995, ISBN 0133601242, third edition 2010, ISBN 0136042597
Planned learning activities and teaching methods
Not applicable.
Assesment methods and criteria linked to learning outcomes
 Midterm written examination  15 points.
 Project  30 points.
 Final written examination  55 points; The minimal number of points necessary for successful clasification is 25 (otherwise, no points will be assigned).
Exam prerequisites:
At least 20 points earned during semester (midterm test and project).
Language of instruction
Czech
Work placements
Not applicable.
Course curriculum
 Syllabus of lectures:
 Introduction. Biological and artificial neuron, artificial neural networks. Perceptron and Adaline.
 Madaline and Back Propagation neural networks.
 RBF, RCE, SCL, /SOFM, LVQ, CPN, ART neural networks.
 Neocognitron and Convolutional neural networks.
 Neural networks as associative memories (Hopfield, BAM, SDM).
 Solving optimization problems using neural networks. Stochastic neural networks, Boltzmann machine.
 Genetic algorithms.
 ACO and PSO optimization algorithms.
 Fuzzy sets and fuzzy logic.
 Probabilistic reasoning, Bayesian networks.
 Rough sets.
 Chaos.
 Hybrid approaches (neural networks, fuzzy logic, genetic algorithms).
Syllabus  others, projects and individual work of students:
Individual project  solving realworld problem (classification, optimization, association, controlling).
Aims
To give students knowledge of softcomputing theories fundamentals, i.e. of fundamentals of nontraditional technologies and approaches to solving hard realworld problems.
Classification of course in study plans
 Programme ITMGR2 Master's
branch MPV , any year of study, winter semester, 5 credits, compulsoryoptional
branch MGM , any year of study, winter semester, 5 credits, elective
branch MSK , any year of study, winter semester, 5 credits, elective
branch MIS , any year of study, winter semester, 5 credits, elective
branch MBS , any year of study, winter semester, 5 credits, elective
branch MMI , any year of study, winter semester, 5 credits, elective
branch MMM , any year of study, winter semester, 5 credits, compulsoryoptional
branch MIN , 1. year of study, winter semester, 5 credits, compulsory
branch MBI , 2. year of study, winter semester, 5 credits, compulsory
Type of course unit
Lecture
26 hours, optionally
Teacher / Lecturer
Syllabus
 Introduction. Biological and artificial neuron, artificial neural networks.
 Acyclic and feedforward neural networks, backpropagation algorithm.
 Neural networks with RBF neurons. Competitive networks.
 Neocognitron and convolutional neural networks.
 Recurrent neural networks (Hopfield networks, Boltzmann machine).
 Recurrent neural networks (LSTM, GRU).
 Genetic algorithms.
 Optimization algorithms inspired by nature.
 Fuzzy sets and fuzzy logic.
 Probabilistic reasoning, Bayesian networks.
 Rough sets.
 Chaos.
 Hybrid approaches (neural networks, fuzzy logic, genetic algorithms).
Project
26 hours, compulsory
Teacher / Lecturer
Syllabus
Individual project  solving realworld problem (classification, optimization, association, controlling).
eLearning
eLearning: currently opened course