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.

This course is intended to provide an overview of modern applications of machine learning and develop practical skills in using deep neural networks for common machine learning tasks. The course provides an introduction into artificial neural network based models, as well as an introduction to existing API frameworks for training such models. Previous knowledge regarding machine learning is not expected. The practical assignments will be developed in Python programming language.

The aim of the course is to familiarize students with the concept of data visualization, selection of techniques and algorithms for visualization of different data sets, and their program implementation. Upon completion of the course is expected the student to demonstrate knowledge of the concept of data visualization, knowledge how to select and implement algorithms for visualizing different data types by programming or by using visualization tools.

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 aim of the course is to provide an insight into the basic procedures of quantitative information processing obtained in research results for programming engineers, using modern information technologies and learning their practical application. To give an initial idea about artificial neural networks and their application possibilities, to be able to apply the use of artificial intelligence methods in real situations.

Introduction to virtualization as a paradigm for creation of virtual computer systems using software virtualization of hardware components. Analysis of different aspects of virtualization, technologies and techniques included in the process, as well as advantages and disadvantages introduces by using virtualization.

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 course gives basic knowledge in programming distributed memory machines using the Message Passing Interface (MPI) industry standard.
After a short introduction to the foundations of HPC and the areas of their application the MPI standard is introduced and some techniques for profiling and debugging of parallel applications are discussed. After thar a detailed presentation of the MPI standard is given, focusing on its implementation for the development of parallel programs. Some specific profiling and fine tuning techniques are introduced.

The course introduces the development of middleware systems. Principles of distributed systems, communication, processing, naming, consistency, replication, security. Application of these concepts in different distributed systems.

An important part of each research study is data and analysis of data in order to arrive at research conclusions and their justification. The activities within the study course examine a formalized intelligent technologies based data analysis process that includes the following steps: definition of a task, data acquisition and pre-processing, data analysis using machine learning / data mining / statistics methods, model assessment, determining biases of data and models, interpretation of results and visualization.

The course introduces students to the theory and application of data visualization. Upon completion the student will be able to demonstrate knowledge of the concept of data visualization, choose and implement visualisation algorithms and use data visualization tools.

The course on the fundamentals of ontology in data mining is intended to provide information technology students with an insight into knowledge structures and their possible applications. The aim of the course is to inform about the approaches and tools that allow the acquisition, description, structuring and use of formally described and structured knowledge. It offers the opportunity to acquire the skills necessary for the creation and application of a knowledge base.

The student will have knowledge about paralel algorithms, parallel architectures, multithreading systems with the ability to create parallel applications and implement optimal deep learning algorithms.

The current course provides knowledge about server virtualization. The students will learn how to setup the server virtualization and how to configure the necessary hardware and virtual machines for development and maintenance of server infrastructure and for computer system administration. The students will work with several operating systems to install and configure the main internet services, including web services, e-mail, ssh, ftp, nfs, etc.

The goal of the course is to study approaches and solutions to overcome the challenges of modelling, management, implementation and deployment of big data production systems.

During the course, students will learn basics about the machine learning techniques and the neural networks, researching the image classification and object detection problems. Students will learn how to work with the machine learning framework Tensorflow, develop new machine learning models as well asuse existing models. Students will learn the cloud platform for model running and learning. During the practical assignments, students will develop software for object detection on the images.

Тo train the students for building advanced intelligent systems with image and sound processing, while solving problems of pattern recognition, classification, ranking in various domains: medicine, engineering, molecular biology. Candidates will be able to design, implement and evaluate the performance of advanced systems using machine learning

The traditional approach to research programmes is to assume that students will find a way to analyse and visualise their data. This assumption brings problems for the students, their supervisors and a significant waste of time. Many students are scared by the data rather than curious and usually skip exploratory data analysis and go straight to advanced statistical models that they cannot explain later because they do not understand their data in depth.

Enabling the students to understand the technologies to discover and extract knowledge from data. The student will be capable to design and develop algorithms for information extraction from enormous amount of data.

As the power and capabilities of computing increases, Artificial Intelligence solutions takes a greater role to perform and execute various processes. Seminar is intended to provide insight into artificial neural networks, give practical examples of deep learning applications and solution implementation using Python and Tensorflow.

Participants will get hands-on experience in implementing deep learning solutions by using Python which currently is one of the most popular programming languages.