681 citations
- Moscow Institute of Physics and TechnologyRU6 papers
- University of LincolnGB3 papers
- Chinese Academy of SciencesCN2 papers
- ITMO UniversityRU2 papers
- Politecnico di MilanoIT2 papers
- Shenzhen Institutes of Advanced TechnologyCN2 papers
- Sobolev Institute of MathematicsRU2 papers
- University of BolognaIT2 papers
- Accenture (Switzerland)CH1 paper
- A.P. Ershov Institute of Informatics Systems, Siberian Branch of the Russian Academy of Sciences1 paper
- Associated Compiler Experts (Netherlands)NL1 paper
- Astana Medical UniversityKZ1 paper
5 papers · 1 filter
How Long short-term memory artificial neural network, synthetic data, and fine-tuning improve the classification of raw EEG data
Albert Nasybullin, Vladimir Maksimenko, Semen Kurkin
In this paper, we discuss a Machine Learning pipeline for the classification of EEG data. We propose a combination of synthetic data generation, long short-term memory artificial n…
Convolutional Neural Network and Adversarial Autoencoder in EEG images classification
Albert Nasybullin, Semen Kurkin
In this paper, we consider applying computer vision algorithms for the classification problem one faces in neuroscience during EEG data analysis. Our approach is to apply a combina…
Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks
Xuewen Dong, Jiachen Li, Shujun Li +4
Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trig…
CayleyPy RL: Pathfinding and Reinforcement Learning on Cayley Graphs
A. Chervov, M. Obozov, A. Soibelman +31
This paper is the second in a series of studies on developing efficient artificial intelligence-based approaches to pathfinding on extremely large graphs (e.g. nodes) wit…
Activations and Gradients Compression for Model-Parallel Training
Mikhail Rudakov, Aleksandr Beznosikov, Yaroslav Kholodov +1
Large neural networks require enormous computational clusters of machines. Model-parallel training, when the model architecture is partitioned sequentially between workers, is a po…