All issues

Traditional classification of real complex networks on biological, technological and social is incomplete, as there is a huge variety of artworks, which structure also can be presented in the form of networks. In this paper the review of researches of the complex networks, modeling some literary, musical and painting works is given. Corresponding networks are offered for naming cognitive networks. The possible directions of studying of such networks are discussed.

Recently, saddle point problems have received much attention due to their powerful modeling capability for a lot of problems from diverse domains. Applications of these problems occur in many applied areas, such as robust optimization, distributed optimization, game theory, and many applications in machine learning such as empirical risk minimization and generative adversarial networks training. Therefore, many researchers have actively worked on developing numerical methods for solving saddle point problems in many different settings. This paper is devoted to developing a numerical method for solving saddle point problems in the nonconvex uniformly-concave setting. We study a general class of saddle point problems with composite structure and H\"older-continuous higher-order derivatives. To solve the problem under consideration, we propose an approach in which we reduce the problem to a combination of two auxiliary optimization problems separately for each group of variables, the outer minimization problem w.r.t. primal variables, and the inner maximization problem w.r.t the dual variables. For solving the outer minimization problem, we use the Adaptive Gradient Method, which is applicable for nonconvex problems and also works with an inexact oracle that is generated by approximately solving the inner problem. For solving the inner maximization problem, we use the Restarted Unified Acceleration Framework, which is a framework that unifies the high-order acceleration methods for minimizing a convex function that has H\"older-continuous higher-order derivatives. Separate complexity bounds are provided for the number of calls to the first-order oracles for the outer minimization problem and higher-order oracles for the inner maximization problem. Moreover, the complexity of the whole proposed approach is then estimated.

In this study we discuss methods to solve optimal control problems based on neural network techniques. We study hierarchical dynamical two-level system for surface water quality control. The system consists of a supervisor (government) and a few agents (enterprises). We consider this problem from the point of agents. In this case we solve optimal control problem with constraints. To solve this problem, we use Pontryagin’s maximum principle, with which we obtain optimality conditions. To solve emerging ODEs, we use feedforward neural network. We provide a review of existing techniques to study such problems and a review of neural network’s training methods. To estimate the error of numerical solution, we propose to use defect analysis method, adapted for neural networks. This allows one to get quantitative error estimations of numerical solution. We provide examples of our method’s usage for solving synthetic problem and a surface water quality control model. We compare the results of this examples with known solution (when provided) and the results of shooting method. In all cases the errors, estimated by our method are of the same order as the errors compared with known solution. Moreover, we study surface water quality control problem when no solutions is provided by other methods. This happens because of relatively large time interval and/or the case of several agents. In the latter case we seek Nash equilibrium between agents. Thus, in this study we show the ability of neural networks to solve various problems including optimal control problems and differential games and we show the ability of quantitative estimation of an error. From the numerical results we conclude that the presence of the supervisor is necessary for achieving the sustainable development.

This paper presents a systematic study of the application of convolutional neural networks (CNNs) as an efficient tool for the analysis of critical and low-temperature phase states in two dimensional spin system models. The problem of calculating the dependence of the average energy $\langle E\rangle_T^{}$ on the spatial distribution of exchange integrals $J_k^{}$ for the Edwards – Anderson model on a square lattice with frustrated interactions is considered.

We further construct a single convolutional classifier of phase states of the ferromagnetic Ising model on square, triangular, honeycomb, and kagome lattices, trained on configurations generated by the Swendsen – Wang cluster algorithm. Сomputed temperature profiles of the averaged posterior probability of the high-temperature phase, form clear S-shaped curves that intersect in the vicinity of the theoretical critical temperatures and allow one to determine $T_c^{}$ for the kagome lattice without additional retraining.

It is shown that convolutional models substantially reduce the root-mean-square error (RMSE) compared with fully connected architectures and efficiently capture complex correlations between thermodynamic characteristics and the structure of magnetic correlated systems.

Explainable Artificial Intelligence (XAI) is a field of artificial intelligence aimed at creating methods and tools for generating interpretable and human-understandable explanations of AI decisions. The relevance of model explainability increases with the deployment of artificial intelligence in critical domains (healthcare, finance, law), where algorithmic opacity can lead to serious consequences for users and society. This work presents an analytical review of the current state of the XAI field, covering theoretical foundations, methodology, and practical applications.

The examined explainable AI methods were selected and systematized based on a multi-level classification of XAI methods by problem formulation (goal, target audience, data type), methodology (application stage, model-specificity, methods, scale), and result form (representation, presentation, evaluation metrics).

A comparative analysis of explainable AI methods for various application domains is conducted. For classical machine learning, SHAP and LIME are examined in detail, revealing their theoretical foundations, computational characteristics, and limitations. For computer vision, gradient-based methods (SmoothGrad, Integrated Gradients), activation visualization methods (Grad-CAM, Grad-CAM++), perturbation-based methods (RISE, Occlusion), and conceptual explanations (TCAV, Network Dissection) are systematized. Special attention is paid to the specifics of applying XAI to natural language processing and large language models, including analysis of the faithfulness of Chain-of-Thought reasoning, natural language explanations, and attribution graph methods. Fundamental limitations of existing approaches to LLM explainability are identified and directions for future research are defined.

The review results demonstrate that XAI methods have reached significant maturity in classical machine learning and computer vision, however, their application to large language models remains an open research problem requiring the development of new explanation paradigms.

The aim of this article is to study the discrete mathematical model of transport network dynamics, recently built by author. The study showed some drawbacks of the basic model and the ways of overcoming these drawbacks, and an improved version of the model was proposed. Simulation systems, created on the basis of this new model were used to do test calculations similar to those previously done with the help of the basic model. The results of these calculations with both models are compared.

The article presents an approach to configuration of an artificial neural network architecture and a training set size. Configuration is based on parameter minimization with constraints specifying neural network model quality criteria. The algorithm of artificial neural network architecture and training set size configuration is applied to dynamic object artificial neural network approximation.
Series of computational experiments were performed. The method is applicable to construction of dynamic object models based on non-linear autocorrelation neural networks.

In this paper, we propose the unified procedure for the development and calibration of mathematical model for multilane urban road traffic flow. We use macroscopic approach, describing traffic flow with the system of second-order nonlinear hyperbolic equations (for traffic density and velocity). We close the resulting model with the equation of vehicle flow as a function of density, obtained empirically for each segment of road network using data from traffic detectors and vehicles’ GPS tracks. We verify the developed new model and calibration methods by using it to model segment of Moscows Ring Road.

The article deals with the development of the noise-reduction algorithm based on anisotropic nonlinear data filtering of computed tomography (CT). Analysis of domestic and foreign literature has shown that the most effective algorithms for noise reduction of CT data use complex methods for analyzing and processing data, such as bilateral, adaptive, three-dimensional and other types of filtrations. However, a combination of such techniques is rarely used in practice due to long processing time per slice. In this regard, it was decided to develop an efficient and fast algorithm for noise-reduction based on simplified bilateral filtration method with three-dimensional data accumulation. The algorithm was developed on C ++11 programming language in Microsoft Visual Studio 2015. The main difference of the developed noise reduction algorithm is the use an improved mathematical model of CT noise, based on the distribution of Poisson and Gauss from the logarithmic value, developed earlier by our team. This allows a more accurate determination of the noise level and, thus, the threshold of data processing. As the result of the noise reduction algorithm, processed CT data with lower noise level were obtained. Visual evaluation of the data showed the increased information content of the processed data, compared to original data, the clarity of the mapping of homogeneous regions, and a significant reduction in noise in processing areas. Assessing the numerical results of the algorithm showed a decrease in the standard deviation (SD) level by more than 6 times in the processed areas, and high rates of the determination coefficient showed that the data were not distorted and changed only due to the removal of noise. Usage of newly developed context dynamic threshold made it possible to decrease SD level on every area of data. The main difference of the developed threshold is its simplicity and speed, achieved by preliminary estimation of the data array and derivation of the threshold values that are put in correspondence with each pixel of the CT. The principle of its work is based on threshold criteria, which fits well both into the developed noise reduction algorithm based on anisotropic nonlinear filtration, and another algorithm of noise-reduction. The algorithm successfully functions as part of the MultiVox workstation and is being prepared for implementation in a single radiological network of the city of Moscow.

In this paper, we consider the problem of restoring the correspondence matrix based on the observations of real correspondences in Moscow. Following the conventional approach [Gasnikov et al., 2013], the transport network is considered as a directed graph whose edges correspond to road sections and the graph vertices correspond to areas that the traffic participants leave or enter. The number of city residents is considered constant. The problem of restoring the correspondence matrix is to calculate all the correspondence from the $i$ area to the $j$ area.

To restore the matrix, we propose to use one of the most popular methods of calculating the correspondence matrix in urban studies — the entropy model. In our work, which is based on the work [Wilson, 1978], we describe the evolutionary justification of the entropy model and the main idea of the transition to solving the problem of entropy-linear programming (ELP) in calculating the correspondence matrix. To solve the ELP problem, it is proposed to pass to the dual problem. In this paper, we describe several numerical optimization methods for solving this problem: the Sinkhorn method and the Accelerated Sinkhorn method. We provide numerical experiments for the following variants of cost functions: a linear cost function and a superposition of the power and logarithmic cost functions. In these functions, the cost is a combination of average time and distance between areas, which depends on the parameters. The correspondence matrix is calculated for multiple sets of parameters and then we calculate the quality of the restored matrix relative to the known correspondence matrix.

We assume that the noise in the restored correspondence matrix is Gaussian, as a result, we use the standard deviation as a quality metric. The article provides an overview of gradient-free optimization methods for solving non-convex problems. Since the number of parameters of the cost function is small, we use the grid search method to find the optimal parameters of the cost function. Thus, the correspondence matrix calculated for each set of parameters and then the quality of the restored matrix is evaluated relative to the known correspondence matrix. Further, according to the minimum residual value for each cost function, we determine for which cost function and at what parameter values the restored matrix best describes real correspondence.