智能决策系统的深度神经网络加速与压缩方法综述  

Review of Acceleration and Compression Methods for Deep Neural Networks in Intelligent Decision Systems

作　　者：黄迪 刘畅 HUANG Di;LIU Chang(School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049, China)

机构地区：[1]中国科学院大学计算机科学与技术学院,北京100049

出　　处：《指挥信息系统与技术》2019年第2期8-13,共6页Command Information System and Technology

基　　金：装备发展部"十三五"预研课题(31511090402)资助项目

摘　　要：深度神经网络凭借其出色的特征提取能力和表达能力,在图像分类、语义分割和物体检测等领域表现出众,对信息决策支持系统的发展产生了重大意义。然而,由于模型存储不易和计算延迟高等问题,深度神经网络较难在信息决策支持系统中得到应用。综述了深度神经网络中低秩分解、网络剪枝、量化、知识蒸馏等加速与压缩方法。这些方法能够在保证准确率的情况下减小深度神经网络模型、加快模型计算,为深度神经网络在信息决策支持系统中的应用提供了思路。For the excellent feature extraction ability and expression ability, the deep neural network does well in the fields of image classification, semantic segmentation and object detection, etc., and it plays a significant role on the development of the information decision support systems. However, for the difficulty of model storage and high computation delay, the deep neural network is difficult to be applied in the information decision support systems. The acceleration and compression methods for the deep neural network, including low-rank decomposition, network pruning, quantization and knowledge distillation are reviewed. The methods can reduce the size of model and speed up the calculation under the condition of ensuring the accuracy, and can provide the idea of the application in the information decision support systems.

关 键 词：深度神经网络 低秩分解 网络剪枝 量化 知识蒸馏 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]