neural networks

Розглядаються питання, пов’язані з розпізнаванням скінченних множин за допомогою двопорогових нейронних елементів. Показано, що задача навчання ДНЕ є NP-повною. Також наведено умови, виконання яких забезпечує двопороговість булевих функцій, які задаються за допомогою списків рішень.

We study finite set dichotomies on bithreshold neurons. We prove that training a BN is NP-complete task. We also give sufficient conditions ensuring that decision list represents a bithreshold function.

The article presents a modern aircraft detection system based on the analysis of sound signals, developed using neural networks and sound analysis algorithms. During the development of the system, the latest technologies were used, such as acoustic sensors, single-board microcomputers and external devices for processing and storing information received from the environment, which ensures fast and accurate detection of aircraft in the air.

Recently, deep learning technologies, namely Neural Networks [1], are attracting more and more attention from businesses and the scientific community, as they help optimize processes and find real solutions to problems much more efficiently and economically than many other approaches. In particular, Neural Networks are well suited for situations when you need to detect objects or look for similar patterns in videos and images, making them relevant in the field of information and measurement technologies in mechatronics and robotics.

With the rapid growth of wind energy production worldwide, the Wind Power Forecast (WPF) will play an increasingly important role in the operation of electricity systems and electricity markets. The article presents an overview of modern methods and tools for forecasting the generation of electricity by wind farms. Particular attention is paid to the intelligent approaches. The article considers the issues of preparation and use of data for such forecasts. It presents the example of a forecasting system based on neural networks, proposed by the authors of the paper.

The article is devoted to the problem of excessive traffic of base station cells. In order to reduce the
impact of this problem on the quality of services of mobile network operators, it is proposed to use
artificial intelligence (AI) technology to analyze and predict the load on the network. AI is great for
wireless environments, as it has a lot of data available for analysis and obtaining certain patterns.
The article proposes a model of machine learning and neural network architecture for forecasting
the load on 5G cells.

The problem of finding objects in images using modern computer vision algorithms has been considered. The description of the main types of algorithms and methods for finding objects based on the use of convolutional neural networks has been given. A comparative analysis and modeling of neural network algorithms to solve the problem of finding objects in images has been conducted. The results of testing neural network models with different architectures on data sets VOC2012 and COCO have been presented.

Data acquisition and processing in cyber-physical system for remote monitoring of the human functional state have been considered in the paper. The data processing steps, strategies for multi-step forecasting evaluation metrics and machine learning algorithms to be implemented have been analysed and described. What is important, this way it will be possible to track the condition of the sick and response to the health changes in advance.

It is shown that for the pro­ces­sing of in­tensi­ve da­ta flows in in­dustry (ma­na­ge­ment of techno­lo­gi­cal pro­ces­ses and complex ob­jects), energy (op­ti­mi­za­ti­on of lo­ad in po­wer grids), mi­li­tary af­fa­irs (techni­cal vi­si­on, mo­bi­le ro­bot traf­fic control, cryptog­raphic da­ta pro­tec­ti­on), transport (traf­fic ma­na­ge­ment and en­gi­ne), me­di­ci­ne (di­se­ase di­ag­no­sis) and instru­men­ta­ti­on (pat­tern re­cog­ni­ti­on and control op­ti­mi­za­ti­on) the re­al-ti­me hardwa­re neu­ral net­works with high ef­fi­ci­ency of eq­uipment use sho­uld be appli­ed.

The review examines the content and main problems of the English-language monograph of the German scientist and philosopher, President of the European Academy of Sciences and Arts, founder of the Munich Center for Social Technologies (MCTS), Honorary Professor of the Technical University of Munich, Professor of Mathematics and Natural Sciences at the Univercity of Tübingen Klaus Mainzer.

This paper explores the finite-time synchronization problem of delayed complex valued neural networks with time invariant uncertainty through improved integral sliding mode control.  Firstly, the master-slave complex valued neural networks are transformed into two real valued neural networks through the method of separating the complex valued neural networks into real and imaginary parts.  Also, the interval uncertainty terms of delayed complex valued neural networks are converted into the real uncertainty terms.  Secondly, a new integral sliding mode surface is designed by employing the ma