摘要
自编码器作为典型的深度无监督学习模型,能够从无标签样本中自动学习样本的有效抽象特征。近年来,自编码器受到广泛关注,已应用于目标识别、入侵检测、故障诊断等众多领域中。基于此,对自编码器的理论基础、改进技术、应用领域与研究方向进行了较全面的阐述与总结。首先,介绍了传统自编码器的网络结构与理论推导,分析了自编码器的算法流程,并与其他无监督学习算法进行了比较。然后,讨论了常用的自编码器改进算法,分析了其出发点、改进方式与优缺点。接着,介绍了自编码器在目标识别、入侵检测等具体领域的实际应用现状。最后,总结了现有自编码器及其改进算法存在的问题,并展望了自编码器的研究方向。
As a typical deep unsupervised learning model, autoencoder can automatically learn effective abstract features from unlabeled samples. In recent years, autoencoder has been widely used in target recognition, intrusion detection, fault diagnosis and many other fields. Thus, the theoretical basis, improved methods, application fields and research directions of autoencoder were described and summarized comprehensively. At first, the network structure, theoretical derivation and algorithm flow of traditional autoencoder were introduced and analyzed, and the difference between autoencoder and other unsupervised learning algorithms was compared. Then, common improved autoencoders were discussed, and their innovation, improvement methods and relative merits were analyzed. Next, the practical application status of autoencoder in target recognition, intrusion detection and other fields were introduced. At last, the existing problems of autoencoder were summarized, and the possible research directions were prospected.
作者
来杰
王晓丹
向前
宋亚飞
权文
LAI Jie;WANG Xiaodan;XIANG Qian;SONG Yafei;QUAN Wen(School of Air and Missile Defense,Air Force Engineering University,Xi’an 710051,China;School of Air Traffic Control and Navigation,Air Force Engineering University,Xi’an 710051,China)
出处
《通信学报》
EI
CSCD
北大核心
2021年第9期218-230,共13页
Journal on Communications
基金
国家自然科学基金资助项目(No.61876189,No.61806219,No.61703426)
陕西省自然科学基础研究计划基金资助项目(No.2021JM-226)。
关键词
自编码器
深度学习
无监督学习
特征提取
正则化
autoencoder
deep learning
unsupervised learning
feature extraction
regularization
