BriefGPT.xyz
Sep, 2015
张量化神经网络
Tensorizing Neural Networks
HTML
PDF
Alexander Novikov, Dmitry Podoprikhin, Anton Osokin, Dmitry Vetrov
TL;DR
本论文研究了如何使用Tensor Train格式转换全连接层的矩阵从而减少深度神经网络的参数数量和计算量,试验结论表明该方法可以将全连接层的参数压缩两百万倍,对整个网络的压缩比可达7倍。
Abstract
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 am
→