9 janv. 2015 - Tensorizing Neural Networks (NIPS 2015)
Description:
tensor-train decomposition (TT decomposition)
将全连接层的权重矩阵转换为 Tensor Train format
In this paper we convert the dense weight matrices of the fully-connected layers to the Tensor Train 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.
结果:
In particular, for the Very Deep VGG networks 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.
Ajouté au bande de temps:
Date: