Описаны структуры и механизмы работы классификатора LiRA и модульных
нейронных сетей. Оба классификатора решают задачу распознавания изображений …

The monograph is devoted to methods and algorithms for the formation of codevectors—
sparse binary vector representations with an adjustable fraction of non-zero components …

Results. A general and additional algorithms for the formation of an individual complex of
control actions for motor and speech functions rehabilitation after a stroke have been …

Purpose of the paper is to discover good decoupling and carrying capacity securing in
moderate dimensions of the antenna elements during the antenna designing for the 5G …

Міри схожості і відстані широко застосовують як в пошуку за схожістю, так і в багатьох
задачах аналізу даних, статистики, машинного навчання тощо. Наприклад, кластерний …

Conclusions. DRs of various data types can be used to improve the efficiency and
intelligence level of information technologies. DRs have been developed for both weakly …

The use of DR allows developing regularization methods for obtaining a stable solution of
discrete ill-posed inverse problems, increasing the computational efficiency and accuracy of …