Course details

Neural Networks

NEU Acad. year 2005/2006 Winter semester 6 credits

Current academic year

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.

Guarantor

Zbořil František, doc. Ing., CSc. (DITS)

Language of instruction

Czech

Completion

Examination

Time span

  • 39 hrs lectures
  • 26 hrs projects

Department

Department of Intelligent Systems (UITS)

Subject specific 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.

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.

Prerequisite knowledge and skills

Fundamentals of mathematical analysis and probability calculus.

Study literature

  • Šíma,J., Neruda,R.: Teoretické otázky neuronových sítí, MATFYZPRESS, 1996, ISBN 80-85863-18-9
  • Novák,M. a kol.: Umělé neuronové sítě, C.H. Beck, 1998, ISBN 80-7179-132-6

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

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

Progress assessment

Study evaluation is based on marks obtained for specified items. Minimimum number of marks to pass is 50.

Controlled instruction

  • Mid-term written examination - 20 points
  • Project - 25 points
Back to top