9 ene 2015 año - Tensorizing Neural Networks (NIPS 2015)

Descripción:

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.