Search

Your search keyword '"D’yakonov, A."' showing total 2,233 results
Start Over Author "D’yakonov, A."
2,233 results on '"D’yakonov, A."'

5. Calibration of Neural Networks

Author

Vasilev, Ruslan and D'yakonov, Alexander

Subjects
Computer Science - Neural and Evolutionary Computing, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Statistics - Machine Learning
Abstract

Neural networks solving real-world problems are often required not only to make accurate predictions but also to provide a confidence level in the forecast. The calibration of a model indicates how close the estimated confidence is to the true probability. This paper presents a survey of confidence calibration problems in the context of neural networks and provides an empirical comparison of calibration methods. We analyze problem statement, calibration definitions, and different approaches to evaluation: visualizations and scalar measures that estimate whether the model is well-calibrated. We review modern calibration techniques: based on post-processing or requiring changes in training. Empirical experiments cover various datasets and models, comparing calibration methods according to different criteria.

Published
2023

11. Learning to Generate Synthetic Training Data using Gradient Matching and Implicit Differentiation

Author

Medvedev, Dmitry and D'yakonov, Alexander

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Neural and Evolutionary Computing, Statistics - Machine Learning
Abstract

Using huge training datasets can be costly and inconvenient. This article explores various data distillation techniques that can reduce the amount of data required to successfully train deep networks. Inspired by recent ideas, we suggest new data distillation techniques based on generative teaching networks, gradient matching, and the Implicit Function Theorem. Experiments with the MNIST image classification problem show that the new methods are computationally more efficient than previous ones and allow to increase the performance of models trained on distilled data.

Published
2022

21. Biocenosis of the vagina. Norm. Disruption. Restoration

Author

Radzinskiy, Viktor, primary, Savicheva, Alevtina, additional, Vorob'ev, Sergey, additional, Spasibova, Elena, additional, Shalepo, Kira, additional, Budilovskaya, Ol'ga, additional, Husnutdinova, Tat'yana, additional, Krysanova, Anna, additional, Guschin, Aleksandr, additional, Raevskaya, Ol'ga, additional, D'yakonov, Sergey, additional, Katkova, Nadezhda, additional, and Yacyshina, Dar'ya, additional

Published
2023
Full Text
View/download PDF

22. New Properties of the Data Distillation Method When Working With Tabular Data

Author

Medvedev, Dmitry and D'yakonov, Alexander

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

Data distillation is the problem of reducing the volume oftraining data while keeping only the necessary information. With thispaper, we deeper explore the new data distillation algorithm, previouslydesigned for image data. Our experiments with tabular data show thatthe model trained on distilled samples can outperform the model trainedon the original dataset. One of the problems of the considered algorithmis that produced data has poor generalization on models with differenthyperparameters. We show that using multiple architectures during distillation can help overcome this problem., Comment: 12 pages

Published
2020

31. Modern Deep Reinforcement Learning Algorithms

Author

Ivanov, Sergey and D'yakonov, Alexander

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning
Abstract

Recent advances in Reinforcement Learning, grounded on combining classical theoretical results with Deep Learning paradigm, led to breakthroughs in many artificial intelligence tasks and gave birth to Deep Reinforcement Learning (DRL) as a field of research. In this work latest DRL algorithms are reviewed with a focus on their theoretical justification, practical limitations and observed empirical properties.

Published
2019

46. New Properties of the Data Distillation Method When Working with Tabular Data

Author

Medvedev, Dmitry, D’yakonov, Alexander, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, van der Aalst, Wil M. P., editor, Batagelj, Vladimir, editor, Ignatov, Dmitry I., editor, Khachay, Michael, editor, Koltsova, Olessia, editor, Kutuzov, Andrey, editor, Kuznetsov, Sergei O., editor, Lomazova, Irina A., editor, Loukachevitch, Natalia, editor, Napoli, Amedeo, editor, Panchenko, Alexander, editor, Pardalos, Panos M., editor, Pelillo, Marcello, editor, Savchenko, Andrey V., editor, and Tutubalina, Elena, editor

Published
2021
Full Text
View/download PDF

49. Natural Acetogenins, Chatenaytrienins-1, -2, -3 and -4, Mitochondrial Potential Uncouplers and Autophagy Inducers—Promising Anticancer Agents

Author

Lilya U. Dzhemileva, Regina A. Tuktarova, Usein M. Dzhemilev, and Vladimir A. D’yakonov

Subjects
acetogenins, chatenaytrienins, cytotoxicity, autophagy, flow cytometry, apoptosis, Therapeutics. Pharmacology, RM1-950
Abstract

The present paper details the complete stereoselective synthesis of four natural acetogenins, chatenaytrienins-1, -2, -3 and -4, previously isolated from the roots of fruit trees of the family Annonaceae (A. nutans and A. muricata), as an inseparable mixture. The novel organometallic reactions, developed by the authors, of Ti-catalyzed cross-cyclomagnesiation of O-containing and aliphatic allenes using available Grignard reagents were applied at the key stage of synthesis. We have studied the biological activity of the synthesized individual chatenaytrienins-1, -2, -3 and -4 in vitro, including their cytotoxicity in a panel of tumor lines and their ability to induce apoptosis, affect the cell cycle and mitochondria, and activate the main apoptotic signaling pathways in the cell, applying modern approaches of flow cytometry and multiplex analysis with Luminex xMAP technology. It has been shown that chatenaytrienins affect mitochondria by uncoupling the processes of mitochondrial respiration, causing the accumulation of ROS ions, followed by the initiation of apoptosis. The most likely mechanism for the death of cortical neurons from the consumption of tea from the seeds of Annona fruit is long-term chronic hypoxia, which leads to the development of an atypical form of Parkinson’s disease that is characteristic of the indigenous inhabitants of Guam and New Caledonia.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results