All issues

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.

In the paper we construct the adjoint problem for the explicit and implicit parabolic quazi-linear grid boundary-value problems with one spatial variable; the coefficients of the problems depend on the solution at the same time and earlier times. Dependence on the history of the solution is via the state vector; its evolution is described by the differential equation. Many models of diffusion mass transport are reduced to such boundary-value problems. Having solutions to the direct and adjoint problems, one can obtain the exact value of the gradient of a functional in the space of parameters the problem also depends on. We present solving algorithms, including the parallel one.

In the paper we consider the inverse problem of evaluating kinetic parameters of the model of dehydriding of metal powder using experimental data. The «blind search» in the space of parameters revealed multiple physically reasonable solutions. The solutions were obtained using high–performance computational modeling based on BOINC–grid.

The work deals the implementation of a three-dimensional mathematical model of the nonlinear time-varying temperature control and a numerical method of solving it.

The paper provides a review of the existing methods of signals’ processing within the conditions of the Rice statistical model applicability. There are considered the principle development directions, the existing limitations and the improvement possibilities concerning the methods of solving the tasks of noise suppression and analyzed signals’ filtration by the example of magnetic-resonance visualization. A conception of a new approach to joint calculation of Rician signal’s both parameters has been developed based on the method of moments in two variants of its implementation. The computer simulation and the comparative analysis of the obtained numerical results have been conducted.

In the work is numerically investigated the influence of elastic and strength characteristics of hard materials with coatings of refractory compounds, received electric-spark doping, at influence of temperature and power factors using the finite element method.

The approach to parallel implementation of low-frequency PIC-algorithms is proposed, taking into account peculiarity of the nonradiative (Darwin) field approximation. Its advantages and specifics of adaptation to the base computer types for high performance calculations are discussed.

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.

We investigate machine learning methods with a certain kind of decision rule. In particular, inverse-distance method of interpolation, method of interpolation by radial basis functions, the method of multidimensional interpolation and approximation, based on the theory of random functions, the last method of interpolation is kriging. This paper shows a method of rapid retraining “model” when adding new data to the existing ones. The term “model” means interpolating or approximating function constructed from the training data. This approach reduces the computational complexity of constructing an updated “model” from $O(n^3)$ to $O(n^2)$. We also investigate the possibility of a rapid assessment of generalizing opportunities “model” on the training set using the method of cross-validation leave-one-out cross-validation, eliminating the major drawback of this approach — the necessity to build a new “model” for each element which is removed from the training set.

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.