SSSD-ECG-nle: New Label Embeddings with Structured State-Space Models for ECG generation

no code implementations • 15 Jul 2024 • Sergey Skorik, Aram Avetisyan

An electrocardiogram (ECG) is vital for identifying cardiac diseases, offering crucial insights for diagnosing heart conditions and informing potentially life-saving treatments.

Local Methods with Adaptivity via Scaling

no code implementations • 2 Jun 2024 • Savelii Chezhegov, Sergey Skorik, Nikolas Khachaturov, Danil Shalagin, Aram Avetisyan, Aleksandr Beznosikov, Martin Takáč, Yaroslav Kholodov, Alexander Gasnikov

A widely used and extensively researched technique to mitigate the communication bottleneck involves performing local training before communication.

Distributed Optimization Federated Learning

Deep Neural Networks Generalization and Fine-Tuning for 12-lead ECG Classification

no code implementations • 19 May 2023 • Aram Avetisyan, Shahane Tigranyan, Ariana Asatryan, Olga Mashkova, Sergey Skorik, Vladislav Ananev, Yury Markin

In this paper, we propose a methodology to improve the quality of heart disease prediction regardless of the dataset by training neural networks on a variety of datasets with further fine-tuning for the specific dataset.

Disease Prediction ECG Classification