Algoritmy a struktury neuropočítačů
Code | Completion | Credits | Range | Language |
---|---|---|---|---|
XE31ASN | Z,ZK | 5 | 2+2s |
- The course is a substitute for:
- Algorithms and Structures of a Neurocomputers (X31ASN)
- Lecturer:
- Tutor:
- 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 recognition and synthesis are investigated in detail. Neural Network Toolbox of Matlab system is used in exercises.
- Requirements:
-
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
2. Neural models, activation functions, learning principles
3. Multilayer networks with back-propagation learning algorithm (BPG)
4. Basic BPG, modifications
5. Optimisation of the structure, neural network pruning, data mining
6. Associative memory, Hopfield networks, ART networks
7. Kohonen's maps, LVQ classifier
8. Basic terms of phonetics, characteristics of the speech
9. Methods of the speech recognition, neural network applications
10. Principles of the speech synthesis, types of the synthesizers
11. Artificial neural networks (ANN) for speech synthesis
12. Special paradigms (CNN, TDNN, Wavelet networks, fuzzy-neural networks)
13. Genetic algorithms
14. The others ANN applications
- Syllabus of tutorials:
-
1. Introduction, Matlab, NN-Toolbox fundamentals, assignment of the semestral projects
2. ANN basic function, Perceptron
3. ADALINE, MADALINE, LMS algorithm
4. Multilayer neural networks
5. Back-propagation algorithm (BPG)
6. Modifications of the BPG algorithm
7. Associative memory (types, learning), Hopfield networks
8. Self-organising maps, LVQ algorithms
9. Presentation of the semestral project thesis - control
10. Pruning - ANN optimisation
11. Semestral projects - consultations
12. Semestral projects - consultations
13. Semestral projects - consultations
14. Semestral projects - evaluation, credits
- Study Objective:
- Study materials:
-
1. Haykin, S.: Neural Networks. A Comprehensive Foundation. Macmillan College Publishing Company, Inc. USA, 1994
2. Kohonen, T.: Self-Organization and Associative Memory. Springer Series in Information Sciences, Berlin, 1984, 1988
3. Simpson, P.K.: Artificial Neural Systems. Foundations Paradigms, Applications and Implementations. Pergamon Press, 1990
- Note:
- Further information:
- No time-table has been prepared for this course
- The course is a part of the following study plans: