BriefGPT.xyz
Nov, 2014
非线性卷积网络的高效准确近似
Efficient and Accurate Approximations of Nonlinear Convolutional Networks
HTML
PDF
Xiangyu Zhang, Jianhua Zou, Xiang Ming, Kaiming He, Jian Sun
TL;DR
本文旨在加速深度卷积神经网络的测试时间计算,通过最小化非线性响应的重建误差,附加一种低秩约束,以帮助降低过滤器的复杂度,该算法可以减小多层输入的叠加误差并提高模型精度,可将ImageNet的训练速度提升4倍,精度提高4.7%。
Abstract
This paper aims to accelerate the
test-time computation
of
deep convolutional neural networks
(CNNs). Unlike existing methods that are designed for approximating linear filters or linear responses, our method tak
→