Cybersicherheitstechnik

I. Content of science:

The goal of teaching science is to teach students the technologies for developing artificial intelligence systems and the methods, models, and algorithmic software tools of neural networks, and to develop the skills to apply them in practice.

The task of science is to provide students with theoretical knowledge, practical skills, and modern methods and tools for building artificial intelligence systems.

II. Main theoretical part (lectures)

The science includes the following topics:

Topic 1. “Artificial Intelligence ” to science entrance

What is artificial intelligence? Fundamentals of artificial intelligence. Areas of application

Topic 2. History of Artificial Intelligence

Stages of development of artificial intelligence. From 2001 to the present - working with large data sets.

Topic 3. Intelligent agents.

Agents and environments. The concept of rationality. The structure of agents

Topic 4. The logic of first-order predicates.

Features of work environments. Agent structure. Agent programs

Topic 5. Problem solving in artificial intelligence.

Solving problems using search algorithms. Problem formulation. Heuristic search strategies.

Topic 6. Finding solutions using classic search.

Search algorithms and optimization problems. Search using nondeterministic actions. Online search agents and unknown environments.

Topic 7. Game theory.

Optimal decisions in games. Partially observable games. Modern game programs

Topic 8. Logical agents .

Knowledge-based agents. Logic. Propositional logic: simple logic. Validating an efficient propositional model. Propositional logic-based agents.

Topic 9. First-order logic.

Syntax and semantics of first-order logic. Using first-order logic

Topic 10. Decision making in first-order logic.

Merge and raise operations. Forward chain algorithm. Reverse chain algorithm.

Topic 11. Expression logic.

Definition of logic. Characteristics of thinking. Term of logic. Laws of logic.

Topic 12. Design issues.

Classical planning approaches and lifting operations. Resources in design: time and planning. Other views of design.

Topic 13. Issues of knowledge presentation.

Objects and events. Intelligent objects and events.

Topic 14. Definition of vague knowledge.

Working under uncertainty. Definition of probability. Bayes' theorem and its applications.

Topic 15. Decision-making under probabilities.

Representing knowledge under uncertainty. Bayesian networks. Bayesian networks in decision making, Markov model. Dynamic Bayesian networks

Topic 16. Prospects for the development of artificial intelligence.

Can a machine be intelligent? Can a machine think? The ethics and risks of developing artificial intelligence.

Topic 17. The current state and future of artificial intelligence.

Representing knowledge under uncertainty. Bayesian networks.

Topic 18. Development and use of expert systems.

Classification of expert systems.

Topic 19. Representing knowledge in expert systems.

Tools for building expert systems.

Topic 20. Types of machine learning.

Supervised and unsupervised learning. Semi-supervised learning. Reinforcement learning algorithms. Transfer learning. Online learning. Batch learning.

Topic 21. Artificial neural networks.

The concept of biological and artificial neurons. The concept of a neural network. Performing logical operations on neurons. The concept and function of a perceptron. Schematic representation of the principle of operation of an artificial neural network. The general recursion rule (GPR) method. Building a simple neural network. Weight coefficients and their calculation. Neural network layers.

Instructions and recommendations for practical training

The following topics are recommended for practical training:

Topic 1 . Purpose and problem to form . Artificial intellect Basics . Areas of application

Topic 2 . The problem solution find . Agents and environments . Rationality The concept of agents structure .

Topic 3 . Artificial intellect level evaluation ( Turing test ) . Turing test , empirical test, its idea

Topic 4 . Intellectual agents create Issues . Agents and environments. Rationality The concept of agents structure .

Topic 5. Machine​ teaching : teacher and without a teacher ( superviser , unsuperviser ). Machine in fact think to receive Is it possible ? Artificial intellect development ethics and risks

Topic 6. Data preprocessing. Search algorithms and optimization problems

Topic 7. Logical​ classifiers . Expert systems classification

Topic 8. Regressors . Regressors​ types and to be used examples . Stochastic regressors , endogenous regressors

Topic 9. Decisions​ tree based on classifier create . Bayesian networks in decision making, Markov model. Dynamic Bayesian networks.

Topic 10. Heuristic​ search . Study of search methods. Search algorithms and optimization problems. Search using nondeterministic actions

Topic 11. In games search algorithms application . Several basic search options and various algorithms for them. Optional functions of linear search.

Topic 12. Studying the Minimax algorithm.

Study of search methods. Application of search algorithms in games. Study of the Minimax algorithm.

Topic 13. Using instrumental tools in machine learning.

Working with the Python programming environment

Topic 14. Linear algebra for machine learning.

Programming linear algebra problems

IV . Independent learning and independent work

The content of independent learning is determined by students

- preparation for lectures and practical exercises;

- doing homework;

- mastering theoretical knowledge;

- performing differentiated individual tasks;

- consists of mastering topics intended for independent study.

Recommended topics for independent study:

1. Artificial intellect in the field of research main directions ;

2. Knowledge system. Knowledge representation models;

3. Understanding of expert system;

4. General information about logic programming;

5. Intelligent systems. The difference between data and information. Properties of knowledge

6. Creating a loop: recursion;

7. Structure, design and functions of intelligent systems;

8. Knowledge representation models. Semantic networks. Advantages and disadvantages of semantic networks;

9. Machine learning and intelligent data analysis.

10. Modern software tools for artificial neural networks. Matlab, C++, Python.

11. Artificial neural networks.

12. Neural Network Programming Methodology

Independent work is the individual work of a student in the form of an abstract, independent work, and presentation on a given task from lectures and practical classes.

V. Results of science teaching (competences to be formed)

Fannie mastery as a result students knowledge need :

• In the process of analyzing the subject area, it is necessary to determine in which areas artificial intelligence can be applied and improved ;

• Machine-made teaching types with to get to know . With a teacher and without a teacher teaching algorithms . Machine learning teaching for analysis of the necessary instrumental tools (Octave/ Matlab /Python) and opportunities with getting to know comes out ;

• Must have the skills to apply general machine learning methods and develop their own thinking algorithms ;

VI. Educational technologies and methods :

• lectures;
• interactive case studies ;
• working in groups;
• making presentations;
• individual projects;
• projects to work and defend as a team .

VII. Requirements for obtaining loans :

Fully master the theoretical and methodological concepts of the subject, be able to correctly reflect the results of the analysis, conduct independent observations of the processes being studied, and complete the tasks and assignments given in the forms of current and intermediate control, and submit a written work for final control.

Main literature

1. H.N.Zaynidinov, T.A.Xo’jaqulov, M.P.Atadjanova. Sun’iy intellekt. O‘quv qo‘llanma. “Aloqachi”, Toshkent, 2018, - 261 b.
2. Q.A.Bekmuratov. Sun’iy intellekt va neyron tarmoqlari (Darslik). – T.: “Mahalla va oila nashriyoti”, 2021. – 373 bet.
3. T.A.Xo‘jaqulov, N.T.Malikova. Sun’iy intellekt. (O‘quv qo‘llanma). – T.: “Aloqachi”, 2019, 192 b.
4. Q.A.Bekmuratov. Sun’iy intellekt. Oliy ta’lim muassasasi talabalari uchun o‘quv qo‘llanma. – T.: “Aloqachi”, 2019. – 312 bet.

Additional literature

1. Мирзиёев Ш.М. Буюк келажагимизни мард ва олижаноб халқимиз билан қурамиз. Тошкент. “Ўзбекистон”, НМИУ, 2017. – 488 б.
2. Мирзиёев Ш.М. Қонун устуворлиги ва инсон манфаатларини таъминлаш – юрт тараққиёти ва халқ фаравонлигинининг гарови. Тошкент. “Ўзбекистон”, НМИУ, 2017. – 48 б.
3. Галушкин А.И. Нейронные сети: основы теории. – М.: Горячая линия. Телеком, 2012. – 496 с.: ил. ISBN 978-5-99-12-0082-0

Internet resources

1. http://tutorialspoint.com
2. http:// ziyonet.uz
3. http://edu.uz
4. https://coursera.org/
5. https://www.guru99.com/deep-learning-tutorial.html