FPF:UIN3042 Artificial Neural Networks - Course Information
UIN3042 Artificial Neural Networks
Faculty of Philosophy and Science in OpavaWinter 2011
- 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 - 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
- Computer Science and Technology (programme FPF, M1801 Inf)
- Computer Science and Technology (programme FPF, N1801 Inf)
- 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, the way and time patterns of transfer of information. Mathematical model of simple neuron and multi-layer neural network.
2. Neural learning schemes. Topology and structure of neural networks.
3. McCuloch-Pitts neurons. Neural networks without feedback: neural models of simple logical functions, learning principles. Training algorithms, the perceptron algorithm.
4. Weight adaptation in networks with one or more hidden layers: the Backpropagation (BP) algorithm. Modifications and improvements of the BP algorithm. Application examples.
5. Associative memories, hetero- and auto-associative networks, synchronous and asynchronous models. Information storage and recall. Learning algorithms, adaptive resonance dynamics. The Lyapunov function and energy.
6. Hopfield model, proof of the principle of minimal energy. Applications: NP-complete problems, data/image reconstruction. Memory capacity of Hopfield networks.
7. Unsupervised learning, Hebb and Oja learnign rule. Networks for extraction of principal components, Sanger rule.
8. Competitive network architecture, Kohonen learnig rule. Clustering, self-organization, variants of learning rules. Self-organizing maps - SOM. Learnign Vector Quantization (LVQ), learning rules for adaptive vector quantization (AVQ).
9. Fuzzy neural networks. Fuzzy neural architecture based on fuzzy arithmetics. Fuzzy neural architecture based on fuzzy logics. Learning schemes for fuzzy neural nets.
- 1. The structure of biological neuron, the way and time patterns of transfer of information. Mathematical model of simple neuron and multi-layer neural network.
- Literature
- recommended literature
- MARČEK, D. Neuronové sítě a fuzzy časové řady. Opava: SU Opava, 2002. ISBN 80-7248-157-6. info
- NERUDA, R., ŠÍMA, J. Teoretické otázky neuronových sítí. Matfyzpress, Praha, 1996. info
- SACKS, O. Muž, který si pletl manželku s kloboukem. Praha: Mladá Fronta, 1993. info
- NOVÁK, M., FABER, J., KUFUDAKI, O. Neuronové sítě a informační systémy živých organismů. Grada, Praha, 1993. info
- HERTZ, J. et. al. Introduction to the Theory of Neural Computation. Addison-Wesley, New York, 1991. info
- Assessment methods
- Oral exam
- Language of instruction
- Czech
- Further Comments
- The course can also be completed outside the examination period.
- Enrolment Statistics (Winter 2011, recent)
- Permalink: https://is.slu.cz/course/fpf/winter2011/UIN3042