SubjectsSubjects(version: 948)
Course, academic year 2023/2024
  
Neural Networks - S445024
Title: Neural Networks
Guaranteed by: Department of Computing and Control Engineering (445)
Faculty: Faculty of Chemical Engineering
Actual: from 2019
Semester: summer
Points: summer s.:5
E-Credits: summer s.:5
Examination process: summer s.:
Hours per week, examination: summer s.:2/2, C+Ex [HT]
Capacity: unknown / unknown (unknown)
Min. number of students: unlimited
Language: English
Teaching methods: full-time
Teaching methods: full-time
Level:  
Is provided by: AM445004
For type:  
Guarantor: Procházka Aleš prof. Ing. CSc.
Examination dates   Schedule   
Annotation
Last update: Procházka Aleš prof. Ing. CSc. (04.07.2012)
The subject presents mathematical models of physiological neural networks and their optimization using evaluated and target values. Problems of global and local optima are presented on the error surface together with the least square method and gradient method for evaluation of optimal structure and network coefficients. Application include signal denoising, prediction and classification with the use in engineering and biomedicine.
Literature
Last update: Procházka Aleš prof. Ing. CSc. (04.07.2012)

[1] S. Haykin: Neural Networks, IEEE Press, 1994

Requirements to the exam
Last update: Procházka Aleš prof. Ing. CSc. (04.07.2012)

During the term three projects are solved and they include application of artificial neural networks for biomedical signal denoising, prediction of environmental data and classification of biomedical data segments. Oral exam includes detail discussion of selected problems and their solution in the MATLAB environment.

Syllabus
Last update: Procházka Aleš prof. Ing. CSc. (04.07.2012)

1. Fundamentals of MATLAB environment, basic operations, data files processing

2. Visualization tools in MATLAB, symbolic mathematics, principles of SIMULINK

3. Basic mathematical models of neurons, transfer functions, threshold, error surface evaluation

4. Single-layer networks, perceptron learning rule, application to classification problems

5. Adaptive linear networks, Widrow-Hoff learning rule, training and coefficients optimization

6. Neural networks in adaptive noise cancellation

7. Multi-layer networks, error function, optimization of parameters, gradient descent method

8. Basic optimization methods (backpropagation, Levenberg-Marquardt algorithm)

9. Neural networks in signal prediction and system modeling, learning and generalization

10. Radial basis networks, transfer functions definition, network structure optimization

11. Associative learning rules, self-organizing networks and maps, Hebian learning, Kohonen rule

12. Neural networks in segmentation, feature extraction and classification, competitive learning

13. Simulation of artificial neural networks in the SIMULINK environment

14. Neural networks in system identification and control, supervised and unsupervised learning

 
VŠCHT Praha