28.08.2022
Despite Russia’s full-blown aggression against Ukraine and the difficult situation, an article by scientists of Artificial Intelligence Department V. Tersiyan and M. Golovyanko “Hyper-flexible Convolutional Neural Networks based on Generalized Lehmer and Power Means” .
The authors of the article also include graduate students D. Malik and V. Branicki, who have been actively engaged in scientific research.
Elsevier’s Neural Networks is the leading journal in the field of artificial intelligence and belongs to Q1 or the top 25% of a subject area.
The paper proposes a new convolutional neural network (CNN) architecture, called hyperflexible, and provides a mathematical justification for the components of such an architecture. It is also experimentally proven that it performs better than the traditional one.
Keeping up the scientific front!
