Zobrazeno 1 - 10
of 895
pro vyhledávání: '"A. Butakov"'
Autor:
Butakov, Ivan, Sememenko, Alexander, Tolmachev, Alexander, Gladkov, Andrey, Munkhoeva, Marina, Frolov, Alexey
Deep InfoMax (DIM) is a well-established method for self-supervised representation learning (SSRL) based on maximization of the mutual information between the input and the output of a deep neural network encoder. Despite the DIM and contrastive SSRL
Externí odkaz:
http://arxiv.org/abs/2410.06993
In this work, we present an AutoTM 2.0 framework for optimizing additively regularized topic models. Comparing to the previous version, this version includes such valuable improvements as novel optimization pipeline, LLM-based quality metrics and dis
Externí odkaz:
http://arxiv.org/abs/2410.00655
Autor:
Zakharova, Anastasiia, Alexandrov, Dmitriy, Khodorchenko, Maria, Butakov, Nikolay, Vasilev, Alexey, Savchenko, Maxim, Grigorievskiy, Alexander
Machine learning (ML) models trained on datasets owned by different organizations and physically located in remote databases offer benefits in many real-world use cases. State regulations or business requirements often prevent data transfer to a cent
Externí odkaz:
http://arxiv.org/abs/2409.15558
Autor:
A. Butakov
Publikováno v:
Правоприменение, Vol 1, Iss 4, Pp 96-111 (2018)
The subject. The article presents a special study of the law enforcement practice of electoral legislation made by a court of various instances in the process of elections to the Omsk City Council of the sixth convocation held on September 10, 2017.
Externí odkaz:
https://doaj.org/article/c4ca9bb1863249358909a2fa52d5a9b2
We propose a novel approach to the problem of mutual information (MI) estimation via introducing a family of estimators based on normalizing flows. The estimator maps original data to the target distribution, for which MI is easier to estimate. We ad
Externí odkaz:
http://arxiv.org/abs/2403.02187
Autor:
A. Butakov
Publikováno v:
Правоприменение, Vol 1, Iss 3, Pp 15-24 (2017)
The subject. The author's research methodology of social processes is represented, by establishinga bond between the ways of property organization and governmental form – especiallyits political regime.The analysis of methodology is based on the hi
Externí odkaz:
https://doaj.org/article/42b1e73b86a74cb592b95cdf46bae383
Autor:
Alan Ling, Sergey Butakov
Publikováno v:
Data Science and Management, Vol 7, Iss 4, Pp 304-313 (2024)
The research community and digital sector are currently engaged in the development of diverse services within the metaverse ecosystems. Conversely, as concerns about safeguarding personal privacy mount, individuals anticipate exercising greater autho
Externí odkaz:
https://doaj.org/article/4b6caf0fde5742e99e6f84e8842de617
Autor:
Butakov, Ivan, Tolmachev, Alexander, Malanchuk, Sofia, Neopryatnaya, Anna, Frolov, Alexey, Andreev, Kirill
The Information Bottleneck (IB) principle offers an information-theoretic framework for analyzing the training process of deep neural networks (DNNs). Its essence lies in tracking the dynamics of two mutual information (MI) values: between the hidden
Externí odkaz:
http://arxiv.org/abs/2305.08013
Autor:
A. N. Ryabikov, M. S. Troshina, M. N. Ryabikov, Yu. Yu. Palekhina, E. O. Butakov, S. K. Malyutina
Publikováno v:
Российский кардиологический журнал, Vol 29, Iss 8 (2024)
Aim. To evaluate the association of flow-mediated vasodilation (FMD) with cardiometabolic diseases (CMDs) and their risk factors (RF) in old age.Material and methods. The study was conducted in the Russian population cohort of the HAPIEE project (Nov
Externí odkaz:
https://doaj.org/article/3f6030427e2742d4be4dbdde56968f2a
Autor:
Ling, Alan, Butakov, Sergey
Publikováno v:
In Data Science and Management December 2024 7(4):304-313