3 papers
cs.CV2021
How saccadic vision might help with theinterpretability of deep networks
Iana Sereda, Grigory Osipov
We describe how some problems (interpretability,lack of object-orientedness) of modern deep networks potentiallycould be solved by adapting a biologically plausible saccadicmechani…
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…