Algorithms and Structures of a Neurocomputers

Lecturer:

Jana Tučková (gar.)

Tutor:

Jana Tučková (gar.)

Supervisor:

Department of Circuit Theory

Synopsis:

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 theory and applications, to the choice and the optimisation of the structures and the neural network applications at the speech analysis, recognition and synthesis are investigated in detail. Some neural network applications in the biomedical engineering are described. Neural Network Toolbox of Matlab system and select special software are used in exercises.

Requirements:

Semestral project thesis - design of original m-file in Matlab, defence of the method of the work.

Syllabus of lectures:

1. Neural networks - research history, biological and artificial neural networks, 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 with Back-Propagation learning algorithm (BPG).

5. Basic BPG, modifications.

6. Optimisation of the structure, neural network pruning, data mining.

7. Basic terms of phonetics, characteristics of the speech.

8. Methods of the speech recognition, neural networks applications.

9. Principles of the speech synthesis, types of the synthesizers, prosody modelling.

10. Artificial neural networks (ANN) for speech synthesis and prosody modelling.

11. Artificial neural networks (ANN) in biomedical engineering.

12. Associative memory, Hopfield networks, ART networks.

13. Special paradigms (CNN, TDNN, Wavelet networks, fuzzy-neural networks). Genetic algorithms.

14. The others ANN applications.

Syllabus of tutorials:

1. Introduction, MATLAB, NN-Toolbox fundamentals, information of the semestral projects.

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. Multilayer neural networks. Assignment of the semestral projects.

6. Modifications of the BPG algorithm.

7. Speech Laboratory - 1st part, experiments.

8. Speech Laboratory - 2nd part, experiments.

9. Presentation of the semestral project thesis - control.

10. Pruning - ANN optimisation. Semestral projects - consultations.

11. Experiments with neural network parameters. Semestral projects - consultations.

12. Programming system ASSOM. Semestral projects - consultations.

13. Semestral projects - consultations.

14. Semestral projects - evaluation, credits.

Study Objective:

Study materials:

1. Tučková, J.: Introduction into the Neural Network Theorie and Applications. Texts of CTU Prague, CTU publishing, 2005, ISBN 80-01-02800-3.

2. Novák, M. a kol.: Artificial Neural Networks, theorie and applications. C.H.Beck, Prague 1998, ISBN 80-7179-732-6.

3. Šnorek, M., Jiřina, M.: Neural Networks and Neurocomputers. Texts of CTU Prague, CTU publishing, 1996.

4. Program library SOM Toolbox 2.0. www.cis.hut.fi/projects/somtoolbox/download.

Note:

Time-table for winter semester 2011/2012:

	06:00–08:0008:00–10:0010:00–12:0012:00–14:0014:00–16:0016:00–18:0018:00–20:0020:00–22:0022:00–24:00
Mon	roomT2:A4-405 Tučková J. 09:15–10:45 (lecture parallel1) Dejvice Laborator
Tue	roomT2:A4-405 Tučková J. 12:45–14:15 (lecture parallel1 parallel nr.1) Dejvice Laborator
Fri
Thu
Fri

Time-table for summer semester 2011/2012:

Time-table is not available yet

The course is a part of the following study plans:

• Electronics - Electronic Systems- structured studies (compulsory course)