arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.08635cs.LG
收藏

深度网络的丢失感知权值Quantization

Loss-aware Weight Quantization of Deep Networks

Department of Computer Science and Engineering(计算机科学与工程系);Hong Kong University of Science and Technology(香港科技大学)

Lu Hou, James T. Kwok

摘要:

深度网络的巨大规模阻碍了它们在小型计算设备中的使用。在本文中,我们考虑压缩网络的重量量化。我们将最近提出的损失感知权重二值化方案扩展到三值化,对于正权重和负权重可能具有不同的缩放参数,以及m位(其中m > 2)量化。在前馈和递归神经网络上的实验表明,该方案优于最先进的权重量化算法,并且与全精度网络一样准确(甚至更准确)。

英文摘要:

The huge size of deep networks hinders their use in small computing devices. In this paper, we consider compressing the network by weight quantization. We extend a recently proposed loss-aware weight binarization scheme to ternarization, with possibly different scaling parameters for the positive and negative weights, and m-bit (where m > 2) quantization. Experiments on feedforward and recurrent neural networks show that the proposed scheme outperforms state-of-the-art weight quantization algorithms, and is as accurate (or even more accurate) than the full-precision network.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑