no code implementations • 16 Apr 2024 • Alexey Kornaev, Elena Kornaeva, Oleg Ivanov, Ilya Pershin, Danis Alukaev
The proposed model regularizes uncertain predictions, and trains to calculate both the predictions and their uncertainty estimations.
1 code implementation • 6 Apr 2022 • Ivan Shchekotov, Pavel Andreev, Oleg Ivanov, Aibek Alanov, Dmitry Vetrov
The FFC operator allows employing large receptive field operations within early layers of the neural network.
2 code implementations • 24 Mar 2022 • Pavel Andreev, Aibek Alanov, Oleg Ivanov, Dmitry Vetrov
Generative adversarial networks have recently demonstrated outstanding performance in neural vocoding outperforming best autoregressive and flow-based models.
3 code implementations • ICLR 2019 • Oleg Ivanov, Michael Figurnov, Dmitry Vetrov
We propose a single neural probabilistic model based on variational autoencoder that can be conditioned on an arbitrary subset of observed features and then sample the remaining features in "one shot".
1 code implementation • 22 Nov 2017 • Oleg Ivanov, Sergey Bartunov
The experimental evaluation shows that this approach significantly increases the quality of cardinality estimation, and therefore increases the DBMS performance for some queries by several times or even by several dozens of times.