|
ИСТИНА |
Войти в систему Регистрация |
ФНКЦ РР |
||
Tensorizing Neural Networksстатья
- Авторы: Alexander Novikov, Dmitry Podoprikhin, Anton Osokin, Dmitry Vetrov
- Журнал: Advances in neural information processing systems
- Том: 28
- Год издания: 2015
- Издательство: Curran Associates
- Местоположение издательства: Red Hook, NY, United States
- Аннотация: Deep neural networks currently demonstrate state-of-the-art performance in several domains. At the same time, models of this class are very demanding in terms of computational resources. In particular, a large amount of memory is required by commonly used fully-connected layers, making it hard to use the models on low-end devices and stopping the further increase of the model size. In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train [17] format such that the number of parameters is reduced by a huge factor and at the same time the expressive power of the layer is preserved. In particular, for the Very Deep VGG networks [21] we report the compression factor of the dense weight matrix of a fully-connected layer up to 200000 times leading to the compression factor of the whole network up to 7 times.
- Добавил в систему: Ветров Дмитрий Петрович