The module is devoted to the evolution approach to artificial intelligence and includes the following sections: Probabilistic optimization algorithms; Genetically oriented evolutionary statements; Genetic operators; Constrained and unconstrained optimization; Software applications; Genetic algorithms; Genetic programming; Evolutionary calculus.
The module is devoted to intelligent computer technologies and includes the following sections: Genetic algorithms for symbolic information processing tasks; Geneticalgorithms for constrained and unconstrained optimization tasks; Pattern recognition and image processing in a fuzzy environment. Intelligent systems as the basis of probabilistic reasoning; Cluster analysis of fuzzy objects; Learning systems in a fuzzy environment; Learning systems in a probabilistic environment; Static fuzzy neurons and networks; Intelligent agents; Hybrid intelligent technologies.
The module is devoted to intelligent computer technologies and includes the following sections: Genetic algorithms for symbolic information processing tasks; Genetic algotirhms for constrained and unconstrained optimization tasks; Knowledge-based systems; Knowledge-based agents; Pattern recognition and image processing in a fuzzy environment; Intelligent systems as the basis of probabilistic reasoning. Learning systems in fuzzy and probabilistic environments; Hybrid intelligent technologies.
Evolutionary mechanisms of biological systems. Genetic operators. Execution cycle of operators. Optimization of multi-criteria and non-linear functions with genetic algorithms. Fundamentals of genetic algorithms adjustment to the task. Fundamentals of genetic programming. Regression analysis using genetic programming. Fundamentals of intelligent agents and the potential of genetic programming in the intelligent-agent-based management.
Data Mining defines a process of mining potentially useful information from data. In most cases it is defined as knowledge discovery from large databases. Data Mining is a technology, which unites traditional data analysis methods with modern algorithms in order to process large amounts of data. This brings a wide range of possibilities for studying and analyzing new and existent types of data, applying new methods.
The course is devoted to the construction of artificial neural networks and includes the following sections: Biological neuron; Artificial neuron; Single layer perceptrons; Straightforward chain networks; Architecture; Learning procedures in single-layer and multi-layer networks; Backward chain networks; Adaptation procedures; Associative memory; Concurrent learning; Software; Neural network applications.
This module is devoted to the construction of artificial neural networks and includes the following sections: Biological neuron; Artificial neuron; Single-layer perceptrons; Straightforward chain networks; Architecture; Learning procedures in single-layer and multi-layer networks; Backward chain networks. Adaptation procedures; Associative memory; Concurrent learning; Software; Neural network applications for information processing.
Architecture and elements of artificial neural networks. Perceptron. Adaptation algorithms. Development of NN technology. Learning methods for single-layer and multi-layer perceptrons. Optimization and forecasting problems. Software. Neurocomputing: algorithms and applications. Design of artificial neural systems: commercial products. Application of artificial neural networks. Cluster analysis. Classification.
The study course covers the theoretical and practical principles of high-performance computing in the context of cybersecurity by using graphics processing hardware and dedicated software. The study course includes an overview of architecture, computing algorithms, software libraries and tools of parallel computing platform CUDA based on graphics processors. An in-depth attention is devoted to the cross-disciplinary application of CUDA in the areas of vulnerability analysis, parallel data encryption, surveillance data mining, object detection and recognition.
The study course covers the theoretical and practical principles of massively parallel high-performance computing that are implemented in a unified framework of multiprocessor systems and specialized software environment. The study course includes an overview of types of high-performance computing hardware and software architecture, computing algorithms, application libraries and tools.
