Персона:
Сбоев, Александр Георгиевич

Организационные подразделения

Организационная единица

Цель ИЯФиТ и стратегия развития - создание и развитие научно-образовательного центра мирового уровня в области ядерной физики и технологий, радиационного материаловедения, физики элементарных частиц, астрофизики и космофизики.

Фамилия

Сбоев

Имя

Александр Георгиевич

Полная страница элемента

Результаты поиска

Теперь показываю 1 - 10 из 49

Открытый доступ
To the question of data-driven identification of author's age for Russian texts with age deceptions using machine learning
(2019) Litvinova, T.; Sboev, A.; Rybka, R.; Moloshnikov, I.; Gudovskikh, D.; Сбоев, Александр Георгиевич
© 2019 Published under licence by IOP Publishing Ltd.In this work we compare data-driven approaches to the task of author's age identification for Russian texts with age deception. The data corpus has been specially gathered with crowdsourcing for this task. Two ways to determine age deception in author texts are considered and compared: The first is a traditional task of identification of age group of a text author, the second is identification of the occurrence of age imitation in the text with its type (imitating higher age or imitating lower age). The best results obtained by LinearSVC model with vector of TF-IDF features of character n-grams as input data demonstrate the F1-score of about 80% for the second task, and for the first one it is about 44%.
Открытый доступ
Data-Driven Model for Emotion Detection in Russian Texts
(2021) Naumov, A.; Rybka, R.; Sboev, A.; Сбоев, Александр Георгиевич
© 2020 Elsevier B.V.. All rights reserved.An important task in the field of automatic data analysis is detecting emotions in texts. The paper presents the approach of emotion recognition for text data in Russian. To conduct an emotion analysis, a method was created based on vector representations of words obtained by the ELMo language model, and subsequent processing by an ensemble classifier. To configure and test the created method, a specially prepared dataset of texts for five basic emotions - joy, sadness, anger, fear, and surprise - is used. The dataset was prepared using a crowdsourcing platform and a home-grown procedure for collecting and controlling annotators' markup. The overall accuracy is 0.78 (by the F1-macro score), which is currently the new state of the art for Russian. The results can be used for a wide range of tasks, for example: monitoring social moods, generating control signals for mobile robotic systems, etc.
Только метаданные
Image and Audio Data Classification Using Bagging Ensembles of Spiking Neural Networks with Memristive Plasticity
(2024) Rybka, R. B.; Davydov, Y.; Sboev, A.; Vlasov, D.; Рыбка, Роман Борисович; Сбоев, Александр Георгиевич
Открытый доступ
Comparison of Bagging and Sparcity Methods for Connectivity Reduction in Spiking Neural Networks with Memristive Plasticity
(2024) Rybka, R.; Davydov, Y.; Vlasov, D.; Sboev, A.; Рыбка, Роман Борисович; Сбоев, Александр Георгиевич
Developing a spiking neural network architecture that could prospectively be trained on energy-efficient neuromorphic hardware to solve various data analysis tasks requires satisfying the limitations of prospective analog or digital hardware, i.e., local learning and limited numbers of connections, respectively. In this work, we compare two methods of connectivity reduction that are applicable to spiking networks with local plasticity; instead of a large fully-connected network (which is used as the baseline for comparison), we employ either an ensemble of independent small networks or a network with probabilistic sparse connectivity. We evaluate both of these methods with a three-layer spiking neural network, which are applied to handwritten and spoken digit classification tasks using two memristive plasticity models and the classical spike time-dependent plasticity (STDP) rule. Both methods achieve an F1-score of 0.93ў??0.95 on the handwritten digits recognition task and 0.85ў??0.93 on the spoken digits recognition task. Applying a combination of both methods made it possible to obtain highly accurate models while reducing the number of connections by more than three times compared to the basic model.
Только метаданные
Baseline accuracy of forecasting COVID-19 cases in Moscow region on a year in retrospect using basic statistical and machine learning methods
(2021) Kudryshov, N. A.; Moloshnikov, I. A.; Serenko, A. V.; Naumov, A. V.; Sboev, A. G.; Сбоев, Александр Георгиевич
© 2021 Institute of Physics Publishing. All rights reserved.The large amount of data that has accumulated so far on the dynamics of the COVID-19 outbreak has allowed to assess the accuracy of forecasting methods in retrospect. This work is devoted to comparing a set of basic time series analysis methods for forecasting the number of confirmed cases for 14 days ahead: machine learning methods, exponential smoothing, autoregressive methods, along with variants of SIR and SEIR. On the year-long data for Moscow, the best basic model is showed to be SEIR within which the basic reproduction number R0 is predicted using a regression model, achieving the mean error of 16% by the MAPE metric. The resulting accuracy can be considered a baseline for a more complex prospective model that would be based on the presented approach.
Только метаданные
Baseline Accuracies of Forecasting COVID-19 Cases in Russian Regions on a Year in Retrospect Using Basic Statistical and Machine Learning Methods
(2021) Naumov, A. V.; Moloshnikov, I. A.; Serenko, A. V.; Rybka, R. B.; Sboev, A. G.; Сбоев, Александр Георгиевич
© 2021 The Author(s).The large amount of data accumulated so far on the dynamics of the COVID-19 outbreak has allowed assessing the accuracy of forecasting methods in retrospect. This work compares several basic time series analysis methods, including machine learning methods, for forecasting the number of confirmed cases for some days ahead. Year-long data for all regions of Russia has been used from the Yandex DataLens platform. As a result, accuracy estimates for these basic methods have been obtained for Russian regions and Russia as a whole, in dependence on the forecasting horizon. The best basic models for forecasting for 14 days are exponential smoothing and ARIMA, with an error of 11-19% by the MAPE metric for the latest part of the course of the epidemic. The accuracies obtained can be considered as baselines for more complex prospective models.
Только метаданные
Modeling the dynamics of spiking networks with memristor-based STDP to solve classification tasks
(2021) Vlasov, D.; Rybka, R.; Davydov, Y.; Serenko, A.; Sboev, A.; Сбоев, Александр Георгиевич
© 2021 by the authors. Licensee MDPI, Basel, Switzerland.The problem with training spiking neural networks (SNNs) is relevant due to the ultra-low power consumption these networks could exhibit when implemented in neuromorphic hardware. The ongoing progress in the fabrication of memristors, a prospective basis for analogue synapses, gives relevance to studying the possibility of SNN learning on the base of synaptic plasticity models, obtained by fitting the experimental measurements of the memristor conductance change. The dynamics of memristor conductances is (necessarily) nonlinear, because conductance changes depend on the spike timings, which neurons emit in an all-or-none fashion. The ability to solve classification tasks was previously shown for spiking network models based on the bio-inspired local learning mechanism of spike-timing-dependent plasticity (STDP), as well as with the plasticity that models the conductance change of nanocomposite (NC) memristors. Input data were presented to the network encoded into the intensities of Poisson input spike sequences. This work considers another approach for encoding input data into input spike sequences presented to the network: temporal encoding, in which an input vector is transformed into relative timing of individual input spikes. Since temporal encoding uses fewer input spikes, the processing of each input vector by the network can be faster and more energy-efficient. The aim of the current work is to show the applicability of temporal encoding to training spiking networks with three synaptic plasticity models: STDP, NC memristor approximation, and PPX memristor approximation. We assess the accuracy of the proposed approach on several benchmark classification tasks: Fisher’s Iris, Wisconsin breast cancer, and the pole balancing task (CartPole). The accuracies achieved by SNN with memristor plasticity and conventional STDP are comparable and are on par with classic machine learning approaches.
Только метаданные
Deep Neural Networks Ensemble with Word Vector Representation Models to Resolve Coreference Resolution in Russian
(2020) Gryaznov, A.; Sboev, A.; Rybka, R.; Сбоев, Александр Георгиевич; Рыбка, Роман Борисович
© 2020, Springer Nature Switzerland AG.In this paper we present a novel neural networks ensemble to solve the task of coreference resolution in Russian texts. The ensemble consists of several neural networks, each based on recurrent Bidirectional long short-term memory layers (BiLSTM), attention mechanism, consistent scoring with selection of probable mentions and antecedents. The applied neural network topology has already shown state-of-the-art results in English for this task, and is now adapted for the Russian language. The resulting coreference markup is obtained by aggregating output scores from several blocks of independently trained neural network models. To represent an input source text, a combination of word vectors from two language models is used. We study the dependence of the coreference detection accuracy on various combinations of models of vector representation of words along with two tokenization approaches: gold markup or UDpipe tools. Finally, to show the improvement made by our ensemble approach, we present the results of experiments with both RuCor and AnCor datasets.
Только метаданные
Solving a classification task by spiking neural network with STDP based on rate and temporal input encoding
(2020) Serenko, A.; Rybka, R.; Sboev, A.; Vlasov, D.; Сбоев, Александр Георгиевич
© 2020 John Wiley & Sons, Ltd.This paper develops local learning algorithms to solve a classification task with the help of biologically inspired mathematical models of spiking neural networks involving the mechanism of spike-timing-dependent plasticity (STDP). The advantages of the models are their simplicity and, hence, the potential ability to be hardware-implemented in low-energy-consuming biomorphic computing devices. The methods developed are based on two key effects observed in neurons with STDP: mean firing rate stabilization and memorizing repeating spike patterns. As the result, two algorithms to solve a classification task with a spiking neural network are proposed: the first based on rate encoding of the input data and the second based on temporal encoding. The accuracy of the algorithms is tested on the benchmark classification tasks of Fisher's Iris and Wisconsin breast cancer, with several combinations of input data normalization and preprocessing. The respective accuracies are 99% and 94% by F1-score.
Только метаданные
A Neural Network Model to Include Textual Dependency Tree Structure in Gender Classification of Russian Text Author
(2020) Selivanov, A.; Rybka, R.; Moloshnikov, I.; Bogachev, D.; Sboev, A.; Сбоев, Александр Георгиевич
© 2020, Springer Nature Switzerland AG.The research proposes the neural network methods to include a textual dependency tree structure in classification tasks of Russian texts. Author profiling task of gender identification was chosen to test the models, and two corpora used in experiments: based on a crowdsource, and in-person polling. The first approach is based on a long short-term memory (LSTM) layers, and developed graph embedding algorithm. The second one is based on a graph convolution network and LSTM. Two syntactic parsers were used to obtain dependency trees from the texts. Input data was represented in different forms: morphological binary vectors, FastText vectors, and their combination. The developed models result was compared to the state-of-the-art, that is neural network model based on a convolutional and LSTM layers. Finally, we demonstrate that including textual dependency tree structure to input feature space improves f1-score of gender classification task on 4% for the RusPersonality dataset, and 7% for the crowdsource dataset in average. The developed models resulting f1-score is 84% and 83%, respectively.