1. Introduction to Artificial Intelligence. Stages of development.
2. Task classes, recognition, adaptation and learning, communication with the machine, problem solving, expert systems. Logical and functional programming style.
3. Cellular automation and their applications.
4. Creation and search in state space. Informed and uninformed search in state space. Options and limitations task solutions using state space.
5. Robot motion control and methods for finding paths in space.
6. Signal processing and analysis. Image and sound signals.
7. Recognize picture and sound. Speech Synthesis.
8. Introduction to Artificial Neural Networks. Biological neural networks and analogy with artificial neural networks.
9. Powerful elements of artificial neural network - formal neuron (neuron input, synaptic scales, neuron threshold, neuron transfer function, neuron activity), neuronal connections, topology of neural networks, artificial neural network training.
10. Perceptron. Networks with threshold (or sigmoid or Heaviside) activation function.
11. Multilayer perceptron - back-propagation network lerning . Network layout, back-propagation algorithm, training and test set, network learning.
12. Disadvantages of redistribution, network paralysis, local minimum, advanced algorithms.
13. Application of Artificial Neural Networks. Speech processing, application of neural networks in the role of analysis and speech recognition, application of neural networks in speech synthesis.
14. Application of neural networks for image processing.

1. Introduction, Work Safety. Determination of requirements for work in the semester.
2. Repetition of work in Matlab and Simulink, unification of knowledge, completion of required knowledge.
3. Design and simulation of cellular automata.
4. Generate and search for state space. Uninformed search methods.
5. Generate and search for state space. Informed search methods.
6. Processing and analysis of camera and microphone signals. Transformation of signal information.
7. Application of methods for image and sound recognition and speech synthesis.
8. Creating and learning a preceptron with a training set.
9. Introducing into the Neural Network Toolbox, the basic features.
10. Preparation for the design of the neural network for the given situation.
11. An example of a neural network design for task of approximation and classification.
12. Assignment of semestral work, design of neural network in Matlab environment for solving given problem.
13. Work on the assignment of the semester work.
14. Presentation of semestral papers, evaluation, credits.