О качестве обучения искусственных нейронных сетей без предобработки исходных данных в условиях их ограниченного набора

Кожемякин Л. В.; А. О. Алексеев

doi:10.15593/2499-9873/2023.3.05

Publications

?

О качестве обучения искусственных нейронных сетей без предобработки исходных данных в условиях их ограниченного набора

Прикладная математика и вопросы управления. 2023. № 3. С. 67–83.

Кожемякин Л. В., Alekseev A.

Research target: Computer Science Clinical Medicine

Language: Russian

DOI

Keywords: нейронные сети

Zα and Zβ Localize ADAR1 to Flipons That Modulate Innate Immunity, Alternative Splicing, and Nonsynonymous RNA Editing

Poptsova M., International Journal of Molecular Sciences 2025 Vol. 26 No. 6 P. 1–21

The double-stranded RNA editing enzyme ADAR1 connects two forms of genetic programming, one based on codons and the other on flipons. ADAR1 recodes codons in pre-mRNA by deaminating adenosine to form inosine, which is translated as guanosine. ADAR1 also plays essential roles in the immune defense against viruses and cancers by recognizing left-handed Z-DNA and ...

Added: June 22, 2026

Международная конференция «Математические идеи академика П.Л. Чебышёва, их приложения в естественных науках и технологи- ях искусственного интеллекта», приуроченная к 205-й годовщине со дня его рождения» : Материалы конференции. / (Обнинск, 14–16 мая 2026 г.): Материалы конференции. Под ред. акад. В.Б. Бетелина. — Калуга: Калужский печатный двор, 2026. — 232 с.

Калужский печатный двор, 2026.

Conference Proceedings INTERNATIONAL CONFERENCE “Mathematical Ideas of Academician P.L. Chebyshev, Their Applications in Natural Sciences and Artificial Intelligence Technologies” dedicated to the 205th anniversary of his birth ...

Added: June 20, 2026

ИНТЕГРАЦИЯ ТЕХНОЛОГИИ ГЕНЕРАТИВНОГО ИСКУССТВЕННОГО ИНТЕЛЛЕКТА В ОБРАЗОВАТЕЛЬНЫЙ ВИДЕОКОНТЕНТ

Stognieva O., Чеснокова Н. Е., Отечественная и зарубежная педагогика 2026 Т. 1 № 3 (115) С. 123–131

Integration of generative artificial intelligence tools into educational practice highlights the need for pedagogically grounded approaches to their use in the creation of educational video content, which is increasingly applied in language and professionally oriented instruction. The purpose of this article is to conduct a comparative analysis of educational video content created using generative AI tools ...

Added: June 20, 2026

Benchmarking DNA large language models on quadruplexes

Cherednichenko O., Herbert A., Poptsova M., Computational and Structural Biotechnology Journal 2025 Vol. 27 P. 992–1000

Large language models (LLMs) in genomics have successfully predicted various functional genomic elements. While their performance is typically evaluated using genomic benchmark datasets, it remains unclear which LLM is best suited for specific downstream tasks, particularly for generating whole-genome annotations. Current LLMs in genomics fall into three main categories: transformer-based models, long convolution-based models, and state-space models ...

Added: June 19, 2026

Kolmogorov–Arnold networks for genomic tasks

Poptsova M., Briefings in Bioinformatics 2025 Vol. 26 No. 2 P. 1–11

Kolmogorov–Arnold networks (KANs) emerged as a promising alternative for multilayer perceptrons (MLPs) in dense fully connected networks. Multiple attempts have been made to integrate KANs into various deep learning architectures in the domains of computer vision and natural language processing. Integrating KANs into deep learning models for genomic tasks has not been explored. Here, we ...

Added: June 19, 2026

Графовые паттерны в несогласованных декларативных моделях процессов

Анненков А. Н., Nesterov R., Моделирование и анализ информационных систем 2026 Т. 33 № 2 С. 176–205

Declarative process models are widely used in process mining to describe flexible process behavior through sets of constraints. However, models discovered automatically from event logs may contain inconsistent constraints, which can make them difficult to interpret and unusable for execution, conformance checking, or further analysis. Existing methods for consistency analysis either rely on automata-based constructions ...

Added: June 18, 2026

Advances in Information Retrieval: 48th European Conference on Information Retrieval, ECIR 2026, Delft, The Netherlands, March 29 – April 2, 2026, Proceedings, Part II. (LNCS, volume 16484)

Cham: Springer Publishing Company, 2026.

The four-volume set LNCS 16483-16486 constitutes the refereed conference proceedings of the 48th European Conference on Information Retrieval, ECIR 2026, held in Delft, The Netherlands, during March 29–April 2, 2026. The 46 full papers and 37 short papers presented together with 10 findings papers, 9 reproducibility papers, 17 resource papers, 11 workshop papers, 7 tutorial papers, ...

Added: June 18, 2026

Искусственный интеллект как роза научной деятельности: исследование Тимоти Гауэрса

Poddiakov A., Троицкий вариант. Наука 2026 № 12 С. 24–25

В научно-популярной заметке представлен обзор содержания поста филдсовского медалиста Тимоти Гауэрса о возможностях ИИ в математике и содержания комментариев под постом. Обзор сделан в основном чат-ботом DeepSeek. В заключение обсуждается возможность не только решения задач искусственным интеллектом, но и их постановки. ...

Added: June 18, 2026

Contribution of attentional mechanisms to verbal and nonverbal communication in boys with ASD

Minnigulova A., Dragoy O., Arutiunian V., European Child and Adolescent Psychiatry 2026

Communication deficits in Autism Spectrum Disorder (ASD) involve impairments in both verbal and nonverbal domains, potentially associated with altered brain network connectivity related to language, attention, and social cognition systems. This study investigated functional connectivity patterns among the Default Mode Network (DMN), Salience Network (SN), Dorsal Attention Network (DAN), and Language Network (LN) in male children ...

Added: June 18, 2026

Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation

Beznosikov A., Kormakov G., Grigorievskiy A. et al., Journal of Optimization Theory and Applications 2026 Vol. 209 Article 18

The objective of Vertical Federated Learning (VFL) is to collectively train a model using features available on different devices while sharing the same users. This paper focuses on the saddle point reformulation of the VFL problem via the classical Lagrangian function. We first demonstrate how this formulation can be solved using deterministic methods.More importantly, we explore various stochastic modifications to ...

Added: June 17, 2026

Supervised Learning in Critical Phenomena—Statistical and Systematic Accuracy

Chertenkov V. I., Shchur L., Lobachevskii Journal of Mathematics 2026 Vol. 47 No. 2 P. 720–727

Supervised machine learning is successfully applied to the study of critical phenomena and allows us to obtain a numerical estimate of the phase transition temperature and the correlation length exponent. We discuss the influence of possible systematic errors, as well as statistical errors, on the accuracy of such numerical estimates. Errors in the training and ...

Added: June 16, 2026

Enhancing Emotion Recognition in Speech Based on Self-Supervised Learning: Cross-Attention Fusion of Acoustic and Semantic Features

Deeb B., Andrey V. Savchenko, Makarov I., IEEE Access 2026 Vol. 13 P. 56283–56295

Speech Emotion Recognition has gained considerable attention in speech processing and machine learning due to its potential applications in human-computer interaction, mental health monitoring, and customer service. However, state-of-the-art models for speech emotion recognition use many parameters, which leads to computational complexity. In this paper, we introduce a novel deep-learning model to enhance the accuracy ...

Added: June 16, 2026

Automated detection of wolf howls using audio spectrogram transformers

Makarov N., Savchenko A., Zemtsova I. et al., Scientific Reports 2025 Vol. 15 Article 26641

The grey wolf (Canis lupus) is a pivotal species for ecological studies. As a key participant in ecosystem processes, it also serves as a model for investigating social structure formation and ecological adaptation. However, the species’ complex social behavior, spatial dynamics, and expansive habitats make monitoring and population assessments across large areas particularly challenging. In recent years, audio traps ...

Added: June 16, 2026

Artificial intelligence framework for multi-pathology risk assessment from retinal fundus images: deep learning approach to 15-disease screening

Vasilev R., Savchenko A., Blinov P. et al., Frontiers in Medicine 2026 Vol. 13

Automated disease screening systems face challenges when applied to multi-class medical image analysis, particularly under severe class imbalance inherent in clinical datasets. Retinal fundus imaging enables non-invasive screening for multiple ocular and systemic diseases simultaneously, yet current automated systems typically assess risk for only a single pathology or a limited disease range. We developed a ...

Added: June 16, 2026

From Data to Signs: A Foundation Model for Multilingual Sign Language Recognition

Novopoltsev M., Tulenkov A., Murtazin R. et al., IEEE Access 2025 Vol. 13 P. 188170–188181

Video-based Isolated Sign Language Recognition (ISLR) problem presents significant challenges in scaling across diverse languages due to data scarcity and the computational costs associated with training of language-specific models. In this paper, we introduce a novel training pipeline that leverages self-supervised learning on a large-scale sign language dataset. To obtain the foundation model, we utilize ...

Added: June 16, 2026

B3Emo: Quantifying Affect as a Double-Edged Sword in Strategic LLM Interactions

Stepin A., Mozikov M., Kabanov A. et al., IEEE Access 2026 Vol. 14 P. 48127–48144

The deployment of large language models (LLMs) in interactive roles such as automated negotiators, customer service agents, and strategic partners requires them to handle not only logical tasks but also the socio-emotional dimensions of interaction. In these situations, success often relies on understanding social cues, building trust, and using persuasion effectively. These skills are closely ...

Added: June 16, 2026

ESQA: Event Sequences Question Answering

Abdullaeva I., Karpukhin I., Filatov A. et al., IEEE Access 2026 Vol. 14 P. 59390–59408

Event sequences, a specialized type of tabular data annotated with timestamps, are prevalent across practical domains such as finance, retail, social networks, and healthcare. Despite the importance of event sequence modeling and analysis, there has been little effort to adapt Large Language Models (LLMs) to this domain. In this paper, we propose a novel solution ...

Added: June 16, 2026

Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Association for Computational Linguistics, 2026.

Added: June 14, 2026

Proceedings of the 6th Workshop on Computational Approaches to Discourse, Context and Document-Level Inferences (CODI 2025)

Strube M., Braud C., Hardmeier C. et al., Suzhou: Association for Computational Linguistics, 2025.

Added: June 11, 2026

Proceedings of the 43rd International Conference on Machine Learning (ICML 2026)

Seul: PMLR, 2026.

Added: June 4, 2026

Stable On-the-Fly Learning for Dynamic Neural Networks With Delayed Inputs

Chertopolokhov V., Mukhamedov A., Bugriy G. et al., IEEE Access 2026 Vol. 14 P. 14369–14392

This study presents on-the-fly identification and multi-step prediction of nonlinear systems with delayed inputs using a dynamic neural network combined with a smooth projection onto ellipsoids. The projection enforces parameter constraints that guarantee stability, while a Lyapunov–Krasovskii analysis yields computable ultimate error bounds. Riccati-type matrix inequalities are derived, providing an efficient vectorization–projection–devectorization implementation suitable for ...

Added: May 22, 2026

Аналитический обзор методов извлечения текстовых транскрипций из речевых высказываний

Ролинский С. О., Dvoynikova A., В кн.: Альманах научных работ молодых ученых Университета ИТМОТ. 2.: Университет ИТМО, 2022. С. 336–340.

В работе рассмотрены основные существующие подходы к автоматическому распознаванию речи, а также проводится сравнительный анализ открытых компьютерных систем распознавания речи. Для экспериментальных исследований эффективности работы рассматриваемых систем используется речевой корпус LibriSpeech. ...

Added: April 24, 2026

Влияние планировщика на обучение нейронных сетей в задаче верификации диктора

Dvoynikova A., Садикова А. А., В кн.: Сборник трудов X Конгресса молодых ученыхТ. 1.: Университет ИТМО, 2021.

В работе рассматривается применение различных планировщиков обучения (англ. scheduler) нейронных сетей для задачи текстонезависимой верификации дикторов. Для экспериментальных исследований использовалась база данных VoxCeleb1, которая содержит в себе различные речевые высказывания 1211 дикторов. В работе проводился анализ влияния различных планировщиков обучения нейронных сетей, представленных в библиотеке PyTorch языка программирования Python, а также 2 алгоритма планировщика, представленных ...

Added: April 24, 2026

Применение ML в целях повышения помехоустойчивости сигналов

Efremov A., Portnoy S., Волошин А. Д., Первая миля 2025 № 8 С. 20–28

Выполнен комплексный обзор методов машинного обучения (ML), применяемых для повышения устойчивости сигнала к помехам в каналах связи. Бурное развитие поколений беспроводной связи, активная разработка концепции 6G предъявляют высокие требования к задержке, скорости и надежности передачи данных. Традиционные подходы к защите от помех, основанные на строгих аналитических моделях, зачастую не справляются с хаотичной природой плотных гетерогенных ...

Added: April 4, 2026