Календарь событий
Структурные модели и глубинное обучение: Acceleration of Convolutional Neural Networks through Elimination of Redundant Convolutions
Понедельник 21 Март 2016, 18:30 - 20:00
Хиты : 84
от Адрес электронной почты защищен от спам-ботов. Для просмотра адреса в вашем браузере должен быть включен Javascript.
Очередное заседание семинара "Структурные модели и глубинное обучение" состоится 21 марта (понедельник), в 18.30, ИППИ, 6 этаж, 615 аудитория.
Охранник на проходной будет предупрежден, проблем с проходом не будет.
Название: Acceleration of Convolutional Neural Networks through Elimination of Redundant Convolutions
Докладчик: Михаил Фигурнов
Аннотация: We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low-power devices such as mobile phones. Inspired by the loop perforation technique from source code optimization, we speed up the bottleneck convolutional layers by skipping their evaluation in some of the spatial positions. We propose and analyze several strategies of choosing these positions. Our method allows to reduce the evaluation time of modern convolutional neural networks by 50% with a small decrease in accuracy.
Охранник на проходной будет предупрежден, проблем с проходом не будет.
Название: Acceleration of Convolutional Neural Networks through Elimination of Redundant Convolutions
Докладчик: Михаил Фигурнов
Аннотация: We propose a novel approach to reduce the computational cost of evaluation of convolutional neural networks, a factor that has hindered their deployment in low-power devices such as mobile phones. Inspired by the loop perforation technique from source code optimization, we speed up the bottleneck convolutional layers by skipping their evaluation in some of the spatial positions. We propose and analyze several strategies of choosing these positions. Our method allows to reduce the evaluation time of modern convolutional neural networks by 50% with a small decrease in accuracy.
Место ИППИ, 6 этаж, 615 аудитория
