###
计算机系统应用:2019,(1):38-46
本文二维码信息
码上扫一扫!
二值网络的分阶段残差二值化算法
任红萍, 陈敏捷, 王子豪, 杨春, 殷绪成
(北京科技大学 计算机与通信工程学院, 北京 100083)
Staged Residual Binarization Algorithm for Binary Networks
REN Hong-Ping, CHEN Min-Jie, WANG Zi-Hao, YANG Chun, YIN Xu-Cheng
(School of Computer & Communication Engineering, University of Science & Technology Beijing, Beijing 100083, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 159次   下载 76
投稿时间:2018-05-22    修订日期:2018-06-15
中文摘要: 二值网络在速度、能耗、内存占用等方面优势明显,但会对深度网络模型造成较大的精度损失.为了解决上述问题,本文提出了二值网络的"分阶段残差二值化"优化算法,以得到精度更好的二值神经网络模型.本文将随机量化的方法与XNOR-net相结合,提出了两种改进算法"带有近似因子的随机权重二值化"和"确定权重二值化",以及一种全新的"分阶段残差二值化"的BNN训练优化算法,以得到接近全精度神经网络的识别准确率.实验表明,本文提出的"分阶段残差二值化"算法能够有效提升二值模型的训练精度,而且不会增加相关网络在测试过程中的计算量,从而保持了二值网络速度快、空间小、能耗低的优势.
Abstract:Binary networks have obvious advantages in terms of speed, energy consumption, and memory consumption, but they cause a great loss of accuracy for the deep network model. In order to solve the problems above, this study proposes a staged residual binarization optimization algorithm for binary networks to obtain a better binary neural network model. In this study, we combine the random quantification method with XNOR-net, and propose two improved algorithms, namely applying weights approximation factor and deterministic quantization networks, and a new staged residual binarization BNN training optimization algorithm, in order to obtain the recognition accuracy of the full-accuracy neural network. Experimental results show that staged residual binarization algorithm can effectively improve the training accuracy of binary model, and does not increase the computational complexity of the related network in the testing process, thus maintaining the advantages of high speed, low memory usage, and small energy consumption.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
任红萍,陈敏捷,王子豪,杨春,殷绪成.二值网络的分阶段残差二值化算法.计算机系统应用,2019,(1):38-46
REN Hong-Ping,CHEN Min-Jie,WANG Zi-Hao,YANG Chun,YIN Xu-Cheng.Staged Residual Binarization Algorithm for Binary Networks.COMPUTER SYSTEMS APPLICATIONS,2019,(1):38-46

用微信扫一扫

用微信扫一扫