UIN3042 Artificial Neural Networks

Faculty of Philosophy and Science in Opava
Winter 2012
Extent and Intensity
2/2/0. 6 credit(s). Type of Completion: zk (examination).
Teacher(s)
prof. Ing. Dušan Marček, CSc. (lecturer)
doc. Ing. Petr Sosík, Dr. (lecturer)
Guaranteed by
doc. Ing. Petr Sosík, Dr.
Institute of Computer Science – Faculty of Philosophy and Science in Opava
Prerequisites
- elementary propositional logic, logic connectives
- differential multivariable calculus, partial derivations, gradient
- elements of object programming (Java, C# etc.)
Course Enrolment Limitations
The course is also offered to the students of the fields other than those the course is directly associated with.
fields of study / plans the course is directly associated with
Course objectives
This classical branch of Artificial Intelligence makes use of mathematical aspects of behavior of neural cells in living organisms. The result is a sequence of "neural" algorithms capable to learn from examples, to generalize knowledge and to search for approximate solutions of intractable problems. These algorithms can be run on special parallel machines but also on classical computers.
Syllabus
  • 1. The structure of biological neuron, mathematical model of a simple neuron and a multi-layer neural network. Features and applications of artificial neural networks.
    2. Active, adaptive and organization dynamics, neural training schemes (supervised/unsupervised/reinforcement). Training and testing sets, training process, the overfitting problem.
    3. The perceptron and its training algorithm. Implementation of simple logic functions. Limited capabilities of single-layer perceptron.
    4. Multilayer networks and the Backpropagation (BP) algorithm. Modifications and improvements of the BP algorithm (training speed adjustment, the momentum term, gain adaptation).

    5. Efficient methods for training of the multilayer perceptron: conjugate-gradient methods, resilient propagation, further methods.
    6. Hetero- and auto-associative networks, topology and training, synchronous and asynchronous models. The Hopfield model, stability and energy, storage capacity
    7. Radial Basis Function networks, organization and active dynamics. Three phases of training, properties, applications, a comparison with multilayer perceptron.
    8. Competitive networks, the vector quantization problem, Lloyd's algorithm. The Kohonen training rule, the UCL, DCL a SCL variants of training.
    9. Self-organizing maps - SOM, description and applications, the neighbourhood function, examples of single- and two-dimensional maps.
    10. The ART networks, principles and properties, the vigilance function.
Literature
    required literature
  • KRIESEL, D. A Brief Introduction to Neural Networks, Zeta version. 2007. URL info
  • NERUDA, R., ŠÍMA, J. Teoretické otázky neuronových sítí. Matfyzpress, Praha, 1996. info
    recommended literature
  • SACKS, O. Muž, který si pletl manželku s kloboukem. Praha: Mladá Fronta, 1993. info
  • HERTZ, J. et. al. Introduction to the Theory of Neural Computation. Addison-Wesley, New York, 1991. info
    not specified
  • MARČEK, D. Neuronové sítě a fuzzy časové řady. Opava: SU Opava, 2002. ISBN 80-7248-157-6. info
Assessment methods
Oral exam
Language of instruction
Czech
Further comments (probably available only in Czech)
The course can also be completed outside the examination period.
The course is also listed under the following terms Winter 1993, Winter 1994, Winter 1995, Winter 1996, Winter 1997, Winter 1998, Winter 1999, Winter 2000, Winter 2001, Winter 2002, Winter 2003, Winter 2004, Summer 2006, Winter 2006, Winter 2007, Winter 2008, Winter 2009, Winter 2010, Winter 2011, Winter 2013, Winter 2014, Winter 2015, Winter 2016, Winter 2017, Winter 2018, Winter 2019, Winter 2020, Winter 2021, Winter 2022, Winter 2023.
  • Enrolment Statistics (Winter 2012, recent)
  • Permalink: https://is.slu.cz/course/fpf/winter2012/UIN3042