Пропуск в контексте
Theoretical Analysis of the Convolutional Neural Networks Acceleration by Organizing Calculations According to the Winograd Method

Theoretical Analysis of the Convolutional Neural Networks Acceleration by Organizing Calculations According to the Winograd Method

Convolutional neural networks are promising tool for pattern recognition. Implementations of convolutional neural networks require a significant number of computations during training and processing. In this paper we propose to use Winograd method to reduce computational complexity in convolutional...

Полное описание

Сохранить в:
Библиографические подробности
Главные авторы: Abdulsalyamova, A. S., Абдулсалямова, А. Ш., Lyakhov, P. A., Ляхов, П. А., Kalita, D. I., Калита, Д. И.
Формат: Статья
Язык:English
Опубликовано: 2023
Темы:
Computational complexity
Digital filtering
Winograd method
Speeding up convolutional neural networks
Convolutional neural networks
Online-ссылка:https://dspace.ncfu.ru/handle/20.500.12258/22737
Метки: Добавить метку
Нет меток, Требуется 1-ая метка записи!

Интернет

https://dspace.ncfu.ru/handle/20.500.12258/22737

Схожие документы