Information about the basic principles and possibility of the application of the neural informative technology for the signal processing are the main topic. The lectures are devoted to the introduction into the artificial neural networks (NN) theory and applications, to the choice and the optimisation of the structures, the choice of the data and the neural network applications at the speech and image processing are investigated in detail. Some neural network applications in the biomedical engineering and hardware realization of the SOM are described. The applications are o focused to EEG and ECG processing, also to possibilities of applications ANN at physiotherapy,
Basic knowledge of the speech and image processing, MATLAB, probability calculus and statistics applications. Active participation on the seminars, develop semester project. More on http://amber.feld.cvut.cz/SSC
1. Neural networks - research history, biological and artificial NN, applications
for signal processing, neural models, activation functions.
2. Learning principles, Self-Organizing Maps (SOM), Kohonen's maps.
3. Supervised SOM, U-matrix, LVQ classifier.
4. Multilayer networks (feedforward and Elman networks) with Back-Propagation learning algorithm (BPG).
5. Basic BPG, modifications.
6. Establish procedure of project by ANN. Optimisation of the structure, Data Mining. neural network pruning, Input data choice
7. Support vector machine learning.
8. ANN and prediction and classification. Basic terms of phonetics, characteristics of the spoken speech (normale and pathological.
9. Special structures ((CNN, TDNN, Wavelet NN, fuzzy-neuron networks). Genetic algorithm.
10. ANN applications in neurology and rehabilitation medicine and in selected medical branches.
11. ECG and EEG processing by ANN.
12. Artificial neural networks (ANN) in speech processing.
13. ANN realizations.
14. The others ANN applications.
1. Introduction, MATLAB, NN-Toolbox fundamentals, information of the semester
2. ANN basic function, Perceptron, ADALINE, MADALINE, LMS algorithm.
3. Self-Organizing Maps, supervised SOM, U-matrix. SOM Toolbox.
4. Kohonen's maps, LVQ algorithms - NN Toolbox, MATLAB.
5. SOM Laboratory - experiments.
6. Multilayer neural networks. Assignment of the semester projects.
7. Modifications of the BPG algorithm.
8. Speech Laboratory - experiments. Assignment of the semester projects.
9. Presentation of the semester project thesis - control.
10. Pruning - ANN optimisation. Semester projects - consultations.
11. Experiments with neural network parameters. Semester projects - consultations.
12. Semester projects - consultations.
13. Hardware implementation of the Kohonen Self-Organizing Maps by FPGA.
14. Semester projects - evaluation, credits.
1. Kohonen,T.: Self-Organizing Maps. Berlin Heidelberg, 3rd Edition, Springer Series in Information Sciences, Springer-Verlag, 2001, ISBN 3-540-67921-9.
2. Handbook of Neural Network Signal Processing.The Electrical Engineering and Applied Signal Processing Series. Ed.: Yu Hen Hu, Jenq-Neng Hwang. CRC Press, USA,2002, ISBN 0-8493-2359-2.
3. Haykin, S.: Neural Networks. A Comprehensive Foundation. Macmillan College Publishing Company, Inc. USA, 1994. 2nd.ed. 1998, Prentice/Hall, Upper Saddle River, NJ.
4. Program library SOM Toolbox 2.0. www.cis.hut.fi/projects/somtoolbox/download