Zobrazeno 1 - 7
of 7
pro vyhledávání: '"D'yakonov, Alexander"'
Autor:
Vasilev, Ruslan, D'yakonov, Alexander
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 probab
Externí odkaz:
http://arxiv.org/abs/2303.10761
Autor:
Medvedev, Dmitry, D'yakonov, Alexander
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 dis
Externí odkaz:
http://arxiv.org/abs/2203.08559
Autor:
Medvedev, Dmitry, D'yakonov, Alexander
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 tabul
Externí odkaz:
http://arxiv.org/abs/2010.09839
Autor:
Ivanov, Sergey, D'yakonov, Alexander
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 r
Externí odkaz:
http://arxiv.org/abs/1906.10025
Autor:
Tsoumakas, Grigorios, Papadopoulos, Apostolos, Qian, Weining, Vologiannidis, Stavros, D'yakonov, Alexander, Puurula, Antti, Read, Jesse, Švec, Jan, Semenov, Stanislav
Publikováno v:
Web Information Systems Engineering - WISE 2014: 15th International Conference, Thessaloniki, Greece, October 12-14, 2014, Proceedings, Part II; 2014, p541-548, 8p
Autor:
D'yakonov, Alexander
Publikováno v:
Rough Sets & Current Trends in Computing (9783642321146); 2012, p432-438, 7p