1 code implementation • 16 Oct 2023 • Arsen Sultanov, Jean-Claude Crivello, Tabea Rebafka, Nataliya Sokolovska
The discovery of new functional and stable materials is a big challenge due to its complexity.
2 code implementations • 4 Mar 2022 • Ariane Marandon, Tabea Rebafka, Etienne Roquain, Nataliya Sokolovska
In this paper the approach is revisited in an unsupervised mixture model framework and the purpose is to develop a method that comes with the guarantee that the false membership rate (FMR) does not exceed a pre-defined nominal level $\alpha$.
1 code implementation • 21 Nov 2020 • Jean-Claude Crivello, Nataliya Sokolovska, Jean-Marc Joubert
Machine learning (ML) methods are becoming integral to scientific inquiry in numerous disciplines, such as material sciences.
no code implementations • 17 Jul 2020 • Nataliya Sokolovska, Pierre-Henri Wuillemin
The approaches based on independence of cause and mechanism state, on the contrary, that causal discovery can be inferred for two observations.
no code implementations • HAL archives-ouvertes 2019 • Asma Atamna, Nataliya Sokolovska, Jean-Claude Crivello
In this work, we present a novel and simple convolutional neural network architecture for supervised learning on graphs that is provably invariant to node permutation.
Ranked #1 on Graph Classification on HYDRIDES
no code implementations • 26 Oct 2018 • Asma Nouira, Nataliya Sokolovska, Jean-Claude Crivello
Our main motivation is to propose an efficient approach to generate novel multi-element stable chemical compounds that can be used in real world applications.
no code implementations • 23 Jun 2018 • Thanh Hai Nguyen, Edi Prifti, Yann Chevaleyre, Nataliya Sokolovska, Jean-Daniel Zucker
Generally, when the sample size ($N$) is much bigger than the number of features ($d$), DL often outperforms other machine learning (ML) techniques, often through the use of Convolutional Neural Networks (CNNs).
no code implementations • 1 Dec 2017 • Thanh Hai Nguyen, Yann Chevaleyre, Edi Prifti, Nataliya Sokolovska, Jean-Daniel Zucker
However, in many bioinformatics ML tasks, we encounter the opposite situation where d is greater than N. In these situations, applying DL techniques (such as feed-forward networks) would lead to severe overfitting.