Neural Networks

Ac.Year:ukončen 2005/2006
EI-BC-3VTB2nd Stage/2nd YearElective
EI-MSC-5VTI2nd Stage/3rd YearElective
Completion:examination (written)
Type of
Hour/semLecturesSem. ExercisesLab. exercisesComp. exercisesOther
Guarantee:Zbořil František V., doc. Ing., CSc., DITS
Lecturer:Zbořil František V., doc. Ing., CSc., DITS
Instructor:Drahanský Martin, doc. Ing., Dipl.-Ing., Ph.D., DITS
Orság Filip, Ing., Ph.D., DITS
Faculty:Faculty of Information Technology BUT
Department:Department of Intelligent Systems FIT BUT
Artificial Intelligence (UIN), DITS
Learning objectives:
  To give the students the knowledge of fundamentals of neural network theory and the knowledge of topologies, learning, responses and possible practical applications of various types of these networks.
  Artificial neuron, basis and activation functions. Classification of neural networks. Principles of individual neural networks (topology, learning, responses, typical applications): "Adaline, Perceptron, Madaline, BPN, adaptive feedforward multilayer networks, self-organizing neural networks, CPN, LVQ, RBF, RCE, Hopfield neural networks, BAM, SDM, Boltzmann machine, Neocognitron". Genetic algorithm, fuzzy systems, rough sets and neural networks.
Knowledge and skills required for the course:
  Fundamentals of mathematical analysis and probability calculus.
Learning outcomes and competences:
  Students acquire knowledge of particular types of neural networks and so they will be able to design programs using these networks to solving of various practical problems.
Syllabus of lectures:
  1. Introduction, artificial neuron, classification of neural networks
  2. Perceptron, Adaline, Madaline
  3. Bacpropagation (BP) Neural Network
  4. Constructive neural networks
  5. RBF and RCE neural networks
  6. Topologic organized neural network, CPN, LVQ
  7. ART and SDM neural networks
  8. Neural networks as associative memories, Hopfield network, BAM
  9. Optimization problems solving using neural networks, Stochastic neural networks, Boltzmann machine
  10. Neocognitron neural network
  11. Genetic algorithm and neural networks
  12. Fuzzy systems and neural networks
  13. Rough sets and neural networks
Syllabus - others, projects and individual work of students:
  • Individual projects - Using of particular neural network for solving some practical problems (as classification, optimization, association)
Fundamental literature:
  • Mehrotra,K., Mohan,C.K., Ranka S: Artificial Neural Networks, The MIT Press, 1997, ISBN 0-262-13328-8
  • Hassoun, M.H.: Artificial Neural Networks, The MIT Press, 1995, ISBN 0-262-08239-X
  • Haykin,S.: Neural Networks, Macmillan College Publishing Company, Inc., 1994, ISBN 0-02-352761-7
Study literature:
  • Sima,J., Neruda,R.: Theoretical questions of neural networks, MATFYZPRESS, 1996, ISBN 80-85863-18-9
  • Novak,M. and others: Artificial neural networks, C.H. Beck, 1998, ISBN 80-7179-132-6
Progress assessment:
  • Mid-term written examination - 20 points
  • Project - 25 points