3 papers
cs.LG2026
Subcritical Signal Propagation at Initialization in Normalization-Free Transformers
Sergey Alekseev
We study signal propagation at initialization in transformers through the averaged partial Jacobian norm (APJN), a measure of gradient amplification across layers. We extend APJN a…
cs.LG2020
Problems of representation of electrocardiograms in convolutional neural networks
Iana Sereda, Sergey Alekseev, Aleksandra Koneva +2
Using electrocardiograms as an example, we demonstrate the characteristic problems that arise when modeling one-dimensional signals containing inaccurate repeating pattern by means…
cs.LG2018
ECG Segmentation by Neural Networks: Errors and Correction
Iana Sereda, Sergey Alekseev, Aleksandra Koneva +2
In this study we examined the question of how error correction occurs in an ensemble of deep convolutional networks, trained for an important applied problem: segmentation of Elect…