<p class="R-AbstractKeywords">There are numerous applications of Artificial Neural Networks (ANN) at the present time and there are different learning algorithms, topologies, hybrid methods etc. It is strongly believed that ANN is built using human brain’s functioning principles but still ANN is very primitive and tricky way for real problem solving. In the recent years modern neurophysiology advanced to a big extent in understanding human brain functions and structure, however, there is a lack of this knowledge application to real ANN learning algorithms. Each learning algorithm and each network topology should be carefully developed to solve more or less complex problem in real life. One may say that almost each serious application requires its own network topology, algorithm and data pre-processing. This article presents a survey of several ways to improve ANN learning possibilities according to human brain structure and functioning, especially one example of this concept – neuroplasticity – automatic adaptation of ANN topology to problem domain.</p>

No abstract

The paper analyses an important problem of cyber security from human safety perspective which is usually described as data and/or computer safety itself without mentioning the human. There are numerous scientific predictions of creation of artificial superintelligence, which could arise in the near future. That is why the strong necessity for protection of such a system from causing any farm arises. This paper reviews approaches and methods already presented for solving this problem in a single article, analyses its results and provides future research directions.

The work shows the role of hidden neurons in the multilayer feed-forward neural networks. The numeric expression of hidden neurons is usually determined in each case empirically. The methodology for determining the number of hidden neurons are described. The neural network based approach is analyzed using a multilayer feed-forward network with backpropagation learning algorithm. We have presented neural network implementation possibility in bankruptcy prediction (the experiments have been performed in the Matlab environment). On the base of bankruptcy data analysis the effect of hidden neurons to specific neural network training quality is shown. The conformity of theoretical hidden neurons to practical solutions was carried out.

The concept of information warfare encompasses the use of information and communication technologies to gain an advantage over a potential opponent. The information warfare is the manipulation with the information that trusts the goal, so that the goal should make decisions about its interests in the interests of opponents. Information structures are treated as systems that process different types of information, provide storage and access to users. Such structures may enclose neural networks, self-learning systems etc. They need to be ready to learn, respond to threats and ensure their safety, which is topical in today's information warfare. This paper will address aspects related to the security of information systems from a system theory point of view. The knowledge base of information structures can be elements of artificial intelligence, which security must be protected against various threats. The authors considers artificial neural networks to be one of the potential threats in the context of information warfare.