All issues

The article provides approaches to evolutionary modelling of synthesis of organised systems and analyses methodological problems of evolutionary computations of this kind. Based on the analysis of works on evolutionary cybernetics, evolutionary theory, systems theory and synergetics, we conclude that there are open problems in formalising the synthesis of organised systems and modelling their evolution. The article emphasises that the theoretical basis for the practice of evolutionary modelling is the principles of the modern synthetic theory of evolution. Our software project uses a virtual computing environment for machine synthesis of problem solving algorithms. In the process of modelling, we obtained the results on the basis of which we conclude that there are a number of conditions that fundamentally limit the applicability of genetic programming methods in the tasks of synthesis of functional structures. The main limitations are the need for the fitness function to track the step-by-step approach to the solution of the problem and the inapplicability of this approach to the problems of synthesis of hierarchically organised systems. We note that the results obtained in the practice of evolutionary modelling in general for the whole time of its existence, confirm the conclusion the possibilities of genetic programming are fundamentally limited in solving problems of synthesizing the structure of organized systems. As sources of fundamental difficulties for machine synthesis of system structures the article points out the absence of directions for gradient descent in structural synthesis and the absence of regularity of random appearance of new organised structures. The considered problems are relevant for the theory of biological evolution. The article substantiates the statement about the biological specificity of practically possible ways of synthesis of the structure of organised systems. As a theoretical interpretation of the discussed problem, we propose to consider the system-evolutionary concept of P.K.Anokhin. The process of synthesis of functional structures in this context is an adaptive response of organisms to external conditions based on their ability to integrative synthesis of memory, needs and information about current conditions. The results of actual studies are in favour of this interpretation. We note that the physical basis of biological integrativity may be related to the phenomena of non-locality and non-separability characteristic of quantum systems. The problems considered in this paper are closely related to the problem of creating strong artificial intelligence.

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.

This paper investigates neural network models and polynomial models based on Chebyshev polynomials for interference compensation. It is shown that the neural network model provides compensation for parasitic interference without the need for parameter tuning, unlike the polynomial model, which requires the selection of optimal delays. The L-BFGS method is applied to both architectures, achieving a compensation level comparable to the LS solution for the polynomial model, with an NMSE result of −23.59 dB and requiring fewer than 2000 iterations, confirming its high efficiency. Additionally, due to the strong generalization ability of neural network architectures, the first-order method for neural networks demonstrates faster convergence compared to the polynomial model. In 20 000 iterations, the neural network model achieves a 0.44 dB improvement in compensation level compared to the polynomial model. In contrast, the polynomial model can only achieve high compensation levels with optimal first-order method parameter tuning, highlighting one of the key advantages of neural network models.

This paper presents the results of experimental validation of some structural issues concerning the practical use of methods to overcome catastrophic forgetting of neural networks. A comparison of current effective methods like EWC (Elastic Weight Consolidation) and WVA (Weight Velocity Attenuation) is made and their advantages and disadvantages are considered. It is shown that EWC is better for tasks where full retention of learned skills is required on all the tasks in the training queue, while WVA is more suitable for sequential tasks with very limited computational resources, or when reuse of representations and acceleration of learning from task to task is required rather than exact retention of the skills. The attenuation of the WVA method must be applied to the optimization step, i. e. to the increments of neural network weights, rather than to the loss function gradient itself, and this is true for any gradient optimization method except the simplest stochastic gradient descent (SGD). The choice of the optimal weights attenuation function between the hyperbolic function and the exponent is considered. It is shown that hyperbolic attenuation is preferable because, despite comparable quality at optimal values of the hyperparameter of the WVA method, it is more robust to hyperparameter deviations from the optimal value (this hyperparameter in the WVA method provides a balance between preservation of old skills and learning a new skill). Empirical observations are presented that support the hypothesis that the optimal value of this hyperparameter does not depend on the number of tasks in the sequential learning queue. And, consequently, this hyperparameter can be picked up on a small number of tasks and used on longer sequences.

The paper provides a method for selecting the composition of a refrigerant with a given isobaric cooling curve using an artificial neural network (ANN). This method is based on the use of 1D layers of a convolutional neural network. To train the neural network, we applied a technological model of a simple heat exchanger in the UniSim design program, using the Peng – Robinson equation of state.We created synthetic database on isobaric boiling curves of refrigerants of different compositions using the technological model. To record the database, an algorithm was developed in the Python programming language, and information on isobaric boiling curves for 1 049 500 compositions was uploaded using the COM interface. The compositions have generated by Monte Carlo method. Designed architecture of ANN allows select composition of a mixed refrigerant by 101 points of boiling curve. ANN gives mole flows of mixed refrigerant by composition (methane, ethane, propane, nitrogen) on the output layer. For training ANN, we used method of cyclical learning rate. For results demonstration we selected MR composition by natural gas cooling curve with a minimum temperature drop of 3 К and a maximum temperature drop of no more than 10 К, which turn better than we predicted via UniSim SQP optimizer and better than predicted by $k$-nearest neighbors algorithm. A significant value of this article is the fact that an artificial neural network can be used to select the optimal composition of the refrigerant when analyzing the cooling curve of natural gas. This method can help engineers select the composition of the mixed refrigerant in real time, which will help reduce the energy consumption of natural gas liquefaction.

The present article describes the authors’ model of construction of the distributed computer network and realization in it of the distributed calculations which are carried out within the limits of the software-information environment providing management of the information, automated and engineering systems of intellectual buildings. The presented model is based on the functional approach with encapsulation of the non-determined calculations and various side effects in monadic calculations that allows to apply all advantages of functional programming to a choice and execution of scenarios of management of various aspects of life activity of buildings and constructions. Besides, the described model can be used together with process of intellectualization of technical and sociotechnical systems for increase of level of independence of decision-making on management of values of parameters of the internal environment of a building, and also for realization of methods of adaptive management, in particular application of various techniques and approaches of an artificial intellect. An important part of the model is a directed acyclic graph, which is an extension of the blockchain with the ability to categorically reduce the cost of transactions taking into account the execution of smart contracts. According to the authors it will allow one to realize new technologies and methods — the distributed register on the basis of the directed acyclic graph, calculation on edge and the hybrid scheme of construction of artificial intellectual systems — and all this together can be used for increase of efficiency of management of intellectual buildings. Actuality of the presented model is based on necessity and importance of translation of processes of management of life cycle of buildings and constructions in paradigm of Industry 4.0 and application for management of methods of an artificial intellect with universal introduction of independent artificial cognitive agents. Model novelty follows from cumulative consideration of the distributed calculations within the limits of the functional approach and hybrid paradigm of construction of artificial intellectual agents for management of intellectual buildings. The work is theoretical. The article will be interesting to scientists and engineers working in the field of automation of technological and industrial processes both within the limits of intellectual buildings, and concerning management of complex technical and social and technical systems as a whole.

This paper investigates the effectiveness of Retrieval-Augmented Generation (RAG) combined with various Large Language Models (LLMs) for document retrieval and information access in corporate information systems. We survey typical use-cases of LLMs in enterprise environments, outline the RAG architecture, and discuss the major challenges that arise when integrating LLMs into a RAG pipeline. A system architecture is proposed that couples a text-vector encoder with an LLM. The encoder builds a vector database that indexes a library of corporate documents. For every user query, relevant contextual fragments are retrieved from this library via the FAISS engine and appended to the prompt given to the LLM. The LLM then generates an answer grounded in the supplied context. The overall structure and workflow of the proposed RAG solution are described in detail. To justify the choice of the generative component, we benchmark a set of widely used LLMs — ChatGPT, GigaChat, YandexGPT, Llama, Mistral, Qwen, and others — when employed as the answer-generation module. Using an expert-annotated test set of queries, we evaluate the accuracy, completeness, linguistic quality, and conciseness of the responses. Model-specific characteristics and average response latencies are analysed; the study highlights the significant influence of available GPU memory on the throughput of local LLM deployments. An overall ranking of the models is derived from an aggregated quality metric. The results confirm that the proposed RAG architecture provides efficient document retrieval and information delivery in corporate environments. Future research directions include richer context augmentation techniques and a transition toward agent-based LLM architectures. The paper concludes with practical recommendations on selecting an optimal RAG–LLM configuration to ensure fast and precise access to enterprise knowledge assets.

Reliable plant disease diagnosis requires not only high classification accuracy, but also stable generalization and interpretable decision-making. Although attention mechanisms are useful to these deep learning models, the performance also depends on where and how they are integrated into the network architecture. This study presents a design-optimized YOLO11m-based classification framework that systematically investigates the impact of Convolutional Block Attention Module (CBAM) injection at different architectural levels for plant disease diagnosis. We perform a comparative modelcontrolled analysis of three model architectures: (i) the baseline YOLO11m-Cls architecture lacking attention, (ii) only adding the backbone block along with CBAM and (iii) a hybrid architecture that includes reduced backbone attention combined with CBAM added at classification head. All models are trained and tested under the same experimental settings using a largescale dataset with around 90 000 images of 38 types of plant diseases. Experimental results clearly show that the uniform injection of CBAM into the backbone reduces stability but causes generalization to worsen with a higher validation loss and significantly lower Top-1 accuracy (≈ 90.5%), while the hybrid attention design balances stability and discrimination, with Top-1 accuracy up to 99.71%, Top-5 accuracy up to 99.99% and near-baseline validation behavior respectively Grad-CAMbased interpretability analysis also demonstrates that the hybrid model generates enhanced and biologically interpretable activation maps, which are more disease-specific with less distraction from background. Notably, the aim of our work is not for achieving superior performance over all classifiers but instead only to provide design-level evidence on how placing attention modulates rigidity and interpretability in YOLO-based classification models. The results provide practical architectural considerations for building dependable and interpretable AI systems in agriculture.