P021 Neural Networks

Faculty of Informatics
Autumn 1999
Extent and Intensity
2/2. 4 credit(s) (plus extra credits for completion). Recommended Type of Completion: zk (examination). Other types of completion: k (colloquium), z (credit).
Teacher(s)
doc. RNDr. Jiří Šíma, DrSc. (lecturer), prof. RNDr. Mojmír Křetínský, CSc. (deputy)
Guaranteed by
prof. RNDr. Mojmír Křetínský, CSc.
Department of Computer Science – Faculty of Informatics
Contact Person: prof. RNDr. Mojmír Křetínský, CSc.
Prerequisites
M001 Calculus II && M004 Linear Algebra II
Prerequisites: M001 Calculus II and M004 Linear Algebra and Geometry II
Course Enrolment Limitations
The course is only offered to the students of the study fields the course is directly associated with.
fields of study / plans the course is directly associated with
Syllabus
  • Introduction to Neural Networks. History of neurocomputing; neurophysiological motivations; mathematical model of neural network: formal neuron, organizational, active, and adaptive dynamics; position of neural networks in computer science: comparison with von Neumann computer architecture, applications, implementations, neurocomputers.
  • Classical Models of Neural Networks. Perceptron: convergence; multi-layered network and backpropagation strategy: choice of topology and generalization; MADALINE: Widrow learning rule.
  • Associative Neural Networks. Linear associative network: Hebb law and pseudohebbian adaptation; Hopfield network: energy, capacity; continuous Hopfield network: traveling salesman problem; Boltzmann machine: simulated annealing, equilibrium.
  • Self-Organization. Kohonen network: unsupervised learning; Kohonen maps; counterpropagation: Grossberg learning rule.
  • Seminar: Software implementation of particular neural network models and their simple applications.
Literature
  • BEALE, R. and T. JACKSON. Neural Computing :An introduction. Bristol: Institute of Physics Publishing, 1994, xv, 240 s. ISBN 0-85274-262-2. info
  • HAYKIN, Simon S. Neural Networks : a comprehensive foundation. New York: Macmillan College Publishing Company, 1994, xix, 696. ISBN 0023527617. info
  • Neural networks - theory and architecture. Edited by Arun Holden - Vitaly I. Kryukov. Manchester: Manchester University Press, 1990, 236 s. ISBN 0-7190-3279-2. info
  • HECHT-NIELSEN, Robert. Neurocomputing. Reading, Mass.: Addison-Wesley Publishing Company, 1990, xiii, 433. ISBN 0-201-09355-3. info
  • Sofsem '88 : sborník referátů : Zotavovna ROH Petr Bezruč, Malenovice, Beskydy 27.11.-9.12.1988. Brno: Ústav výpočetní techniky UJEP Brno, 1988, 363 s. info
Language of instruction
Czech
Further Comments
The course is taught annually.
The course is taught: every other week.
The course is also listed under the following terms Autumn 1995, Autumn 1996, Autumn 1998, Spring 2001, Autumn 2001.
  • Enrolment Statistics (Autumn 1999, recent)
  • Permalink: https://is.muni.cz/course/fi/autumn1999/P021