自编码器及其应用综述

doi:10.11959/j.issn.1000-436x.2021160

通信学报 ›› 2021, Vol. 42 ›› Issue (9): 218-230.doi: 10.11959/j.issn.1000-436x.2021160

自编码器及其应用综述

来杰¹, 王晓丹¹, 向前¹, 宋亚飞¹, 权文²

¹ 空军工程大学防空反导学院，陕西西安 710051
² 空军工程大学空管领航学院，陕西西安 710051

修回日期:2021-07-29 出版日期:2021-09-25 发布日期:2021-09-01
作者简介:来杰（1994− ），男，四川简阳人，空军工程大学博士生，主要研究方向为机器学习及其在目标识别、入侵检测等领域中的应用
王晓丹（1966− ），女，陕西汉中人，博士，空军工程大学教授，主要研究方向为机器学习及其在目标识别、入侵检测等领域中的应用
向前（1995− ），男，四川广元人，空军工程大学博士生，主要研究方向为机器学习及其在目标识别、入侵检测等领域中的应用
宋亚飞（1988− ），男，河南汝州人，博士，空军工程大学副教授，主要研究方向为机器学习及其在目标识别、入侵检测等领域中的应用
权文（1988− ），女，陕西蒲城人，博士，空军工程大学讲师，主要研究方向为机器学习及其在空管领航、目标识别等领域中的应用
基金资助:
国家自然科学基金资助项目(61876189);国家自然科学基金资助项目(61806219);国家自然科学基金资助项目(61703426);陕西省自然科学基础研究计划基金资助项目(2021JM—226)

Review on autoencoder and its application

Jie LAI¹, Xiaodan WANG¹, Qian XIANG¹, Yafei SONG¹, Wen QUAN²

¹ School of Air and Missile Defense, Air Force Engineering University, Xi’an 710051, China
² School of Air Traffic Control and Navigation, Air Force Engineering University, Xi’an 710051, China

Revised:2021-07-29 Online:2021-09-25 Published:2021-09-01
Supported by:
The National Natural Science Foundation of China(61876189);The National Natural Science Foundation of China(61806219);The National Natural Science Foundation of China(61703426);The Natural Science Basic Research Plan in Shaanxi Province(2021JM—226)

摘要/Abstract

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。

关键词: 自编码器, 深度学习, 无监督学习, 特征提取, 正则化

Abstract:

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.

Key words: autoencoder, deep learning, unsupervised learning, feature extraction, regularization

中图分类号:

TP183

来杰, 王晓丹, 向前, 宋亚飞, 权文. 自编码器及其应用综述[J]. 通信学报, 2021, 42(9): 218-230.

Jie LAI, Xiaodan WANG, Qian XIANG, Yafei SONG, Wen QUAN. Review on autoencoder and its application[J]. Journal on Communications, 2021, 42(9): 218-230.

图/表 6

图1

表1

图2

图3

图4

表2

自编码器改进算法的分析与比较"

算法	出发点	改进方式
传统正则化自编码器	调整权值衰减程度，改善过拟合现象	在自编码器损失函数中添加权值的L₂范数正则化项
稀疏自编码器	增强所提取特征的稀疏性	在自编码器损失函数中添加隐含层输出的KL散度正则化项
去噪自编码器	改善噪声影响，提升所提取特征的稳健性	引入退化过程，用添加噪声的输入样本重构原始纯净样本
收缩自编码器	提升所提取特征对输入小扰动的稳健性	在自编码器损失函数中添加隐含层输出的收缩正则化项
变分自编码器	迫使隐变量满足特定分布，具备数据生成能力	添加隐变量分布的KL正则化项，引入重参数技巧将采样计算变为数值计算
卷积自编码器	保留图像的空间信息	将自编码器的全连接层替换为卷积层与池化层
极限学习机-自编码器	改善泛化性能，提升训练效率	随机赋值隐含层输入权值与偏置，并计算输出权值的最小二乘解
区分自编码器	增强所提取特征的可区分性	在自编码器损失函数中添加隐含层输出的类内距离与类间距离正则化项
L₂₁范数自编码器	兼顾所提取特征的稀疏性与稳健性	在自编码器损失函数中添加隐含层输出的L₂₁范数正则化项
对抗自编码器	迫使隐变量满足特定分布，提升数据生成能力	引入对抗学习策略，完成隐变量向特定分布的逼近
图自编码器	保持低维流形的局部一致性	通过引入迹函数，在自编码器损失函数中添加图正则化项
二次自编码器	提升所提取抽象特征的稳健性	采用输入样本的二次运算代替传统神经节点的内积，提出了二次神经节点，并构建其自编码器结构
狄利克雷变分自编码器	提升生成样本的对数似然性，避免解码器权值崩溃	将变分自编码器假设的高斯分布替换为狄利克雷分布，利用随机梯度下降拟合其分布函数
注意力协同自编码器	提升局部关键信息的重要程度	将注意力机制引入自编码器中，在反向传播中实现关键特征的重新加权
同构自编码器	降低重构误差，使抽象特征更能描述输入样本数据结构	在堆栈自编码器中，将各层自编码器期望输出均替换为原始输入样本

表2

参考文献 80

[1]	HINTON G E , SALAKHUTDINOV R R . Reducing the dimensionality of data with neural networks[J]. Science, 2006,313(5786): 504-507.
[2]	BENGIO Y , COURVILLE A , VINCENT P . Representation learning:a review and new perspectives[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013,35(8): 1798-1828.
[3]	SCHOLKOPF B , PLATT J , HOFMANN T . Greedy layer-wise training of deep networks[J]. Advances in Neural Information Processing Systems, 2007,19: 153-160.
[4]	袁非牛, 章琳, 史劲亭 ,等. 自编码神经网络理论及应用综述[J]. 计算机学报, 2019,42(1): 203-230.
	YUAN F N , ZHANG L , SHI J T ,et al. Theories and applications of auto-encoder neural networks:a literature survey[J]. Chinese Journal of Computers, 2019,42(1): 203-230.
[5]	RUMELHART D E , HINTON G E , WILLIAMS R J . Learning representations by back-propagating errors[J]. Nature, 1986,323(6088): 533-536.
[6]	BOURLARD H , KAMP Y . Auto-association by multilayer perceptrons and singular value decomposition[J]. Biological Cybernetics, 1988,59(4/5): 291-294.
[7]	SALAKHUTDINOV R , HINTON G . Deep boltzmann machines[C]// Proceedings of the Twelfth International Conference on Artificial Intelligence and Statistics. Clearwater Beach:MLRP, 2009: 448-455.
[8]	FISCHER A , IGEL C . Training restricted Boltzmann machines:an introduction[J]. Pattern Recognition, 2014,47(1): 25-39.
[9]	GOODFELLOW I , POUGET-ABADIE J , MIRZA M ,et al. Generative adversarial nets[C]// Proceedings of the Advances in Neural Information Processing Systems. Massachusetts:MIT Press, 2014: 2672-2680.
[10]	NG A . Sparse autoencoder[J]. CS294A Lecture Notes, 2011,72(1): 1-19.
[11]	VINCENT P , LAROCHELLE H , LAJOIE I ,et al. Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J]. Journal of Machine Learning Research, 2010,11(12): 3371-3408.
[12]	RIFAI S , VINCENT P , MULLER X ,et al. Contractive auto-encoders:explicit invariance during feature extraction[C]// Proceedings of the 28th International Conference on Machine Learning. Bellevue:Omnipress, 2011: 833-840.
[13]	KINGMA D P , WELLING M . Auto-encoding variational bayes[J]. arXiv Preprint,arXiv:1312.6114, 2013.
[14]	MIAN P , JIE J , ZHU L ,et al. Radar HRRP recognition based on discriminant deep autoencoders with small training data size[J]. Electronics Letters, 2016,52(20): 1725-1727.
[15]	FENG B , CHEN B , LIU H W . Radar HRRP target recognition with deep networks[J]. Pattern Recognition, 2017,61: 379-393.
[16]	LI Y C , MA R , JIAO R H . A hybrid malicious code detection method based on deep learning[J]. International Journal of Security and Its Applications, 2015,9(5): 205-216.
[17]	JAVAID A , NIYAZ Q , SUN W Q ,et al. A deep learning approach for network intrusion detection system[C]// Proceedings of the 9th EAI International Conference on Bio-inspired Information and Communications Technologies. New York:ACM Press, 2016: 21-26.
[18]	ZHANG Y Y , GAO L , LI X Y ,et al. A novel data-driven fault diagnosis method based on deep learning[C]// International Conference on Data Mining and Big Data. Berlin:Springer, 2017: 442-452.
[19]	LU C , WANG Z Y , QIN W L ,et al. Fault diagnosis of rotary machinery components using a stacked denoising autoencoder-based health state identification[J]. Signal Processing, 2017,130: 377-388.
[20]	ZHANG J , YU J , TAO D C . Local deep-feature alignment for unsupervised dimension reduction[J]. IEEE Transactions on Image Processing, 2018,27(5): 2420-2432.
[21]	WANG J L , HOU B , JIAO L C ,et al. POL-SAR image classification based on modified stacked autoencoder network and data distribution[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020,58(3): 1678-1695.
[22]	LIU C , TANG L X , LIU J Y . A stacked autoencoder with sparse Bayesian regression for end-point prediction problems in steelmaking process[J]. IEEE Transactions on Automation Science and Engineering, 2020,17(2): 550-561.
[23]	KOHONEN T , HONKELA T . Kohonen network[J]. Scholarpedia, 2007,2(1): 1568.
[24]	胡铭菲, 刘建伟, 左信 . 深度生成模型综述[J]. 自动化学报, 2020,41: 1-35.
	HU M F , LIU J W , ZUO X . Survey on deep generative model[J]. Acta Automatica Sinica, 2020,41: 1-35.
[25]	翟正利, 梁振明, 周炜 ,等. 变分自编码器模型综述[J]. 计算机工程与应用, 2019,55(3): 1-9.
	ZHAI Z L , LIANG Z M , ZHOU W ,et al. Research overview of variational auto-encoders models[J]. Computer Engineering and Applications, 2019,55(3): 1-9.
[26]	MASCI J , MEIER U , CIRE?AN D ,et al. Stacked convolutional auto-encoders for hierarchical feature extraction[C]// Lecture Notes in Computer Science. Berlin:Springer, 2011: 52-59.
[27]	KASUN L L C , ZHOU H , HUANG G B ,et al. Representational learning with extreme learning machine for big data[J]. IEEE Intelligent Systems, 2013,28(6): 31-34.
[28]	XIE J , FANG Y , ZHU F ,et al. Deepshape:deep learned shape descriptor for 3D shape matching and retrieval[C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway:IEEE Press, 2015: 1275-1283.
[29]	LI R , WANG X D , LEI L ,et al. L₂₁-norm based loss function and regularization extreme learning machine[J]. IEEE Access, 2019,7: 6575-6586.
[30]	MAKHZANI A , SHLENS J , JAITLY N ,et al. Adversarial autoencoders[J]. arXiv Preprint,arXiv:1511.05644, 2015.
[31]	MAJUMDAR A . Graph structured autoencoder[J]. Neural Networks, 2018,106: 271-280.
[32]	FAN F L , SHAN H M , KALRA M K ,et al. Quadratic autoencoder (Q-AE) for low-dose CT denoising[J]. IEEE Transactions on Medical Imaging, 2020,39(6): 2035-2050.
[33]	JOO W , LEE W , PARK S ,et al. Dirichlet variational autoencoder[J]. Pattern Recognition, 2020,107: 107514-2050.
[34]	CHEN S , WU M . Attention collaborative autoencoder for explicit recommender systems[J]. Electronics, 2020,9(10): 1716.
[35]	YUAN X F , WANG Y L , YANG C H ,et al. Stacked isomorphic autoencoder based soft analyzer and its application to sulfur recovery unit[J]. Information Sciences, 2020,534: 72-84.
[36]	WANG X D , LI R , WANG J ,et al. One-dimension hierarchical local receptive fields based extreme learning machine for radar target HRRP recognition[J]. Neurocomputing, 2020,418: 314-325.
[37]	ZHAO F X , LIU Y X , HUO K ,et al. Radar HRRP target recognition based on stacked autoencoder and extreme learning machine[J]. Sensors, 2018,18(2): 173.
[38]	CHEN X Y , PENG X Y , LI J B ,et al. Sparse autoencoder based manifold analyzer model of multi-angle target feature[J]. IEEE Access, 2020,8: 153250-153263.
[39]	KANG M , JI K F , LENG X G ,et al. Synthetic aperture radar target recognition with feature fusion based on a stacked autoencoder[J]. Sensors, 2017,17(12): 192-197.
[40]	DENG S , DU L , LI C ,et al. SAR automatic target recognition based on euclidean distance restricted autoencoder[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017,10(7): 3323-3333.
[41]	DONG G G , LIAO G S , LIU H W ,et al. A review of the autoencoder and its variants:a comparative perspective from target recognition in synthetic-aperture radar images[J]. IEEE Geoscience and Remote Sensing Magazine, 2018,6(3): 44-68.
[42]	GUO J , WANG L , ZHU D Y ,et al. Compact convolutional autoencoder for SAR target recognition[J]. IET Radar,Sonar ＆ Navigation, 2020,14(7): 967-972.
[43]	MISHRA P , VARADHARAJAN V , TUPAKULA U ,et al. A detailed investigation and analysis of using machine learning techniques for intrusion detection[J]. IEEE Communications Surveys ＆ Tutorials, 2019,21(1): 686-728.
[44]	AL-QATF M , YU L S , AL-HABIB M , ,et al. Deep learning approach combining sparse autoencoder with SVM for network intrusion detection[J]. IEEE Access, 2018,6: 52843-52856.
[45]	CAO V L , NICOLAU M , MCDERMOTT J . Learning neural representations for network anomaly detection[J]. IEEE Transactions on Cybernetics, 2019,49(8): 3074-3087.
[46]	CHOUHAN N , KHAN A , KHAN H U R . Network anomaly detection using channel boosted and residual learning based deep convolutional neural network[J]. Applied Soft Computing, 2019,83: 105612.
[47]	LOPEZ-MARTIN M , CARRO B , SANCHEZ-ESGUEVILLAS A , . Variational data generative model for intrusion detection[J]. Knowledge and Information Systems, 2019,60(1): 569-590.
[48]	IERACITANO C , ADEEL A , MORABITO F C ,et al. A novel statistical analysis and autoencoder driven intelligent intrusion detection approach[J]. Neurocomputing, 2020,387: 51-62.
[49]	TANG C F , LUKTARHAN N , ZHAO Y X . SAAE-DNN:deep learning method on intrusion detection[J]. Symmetry, 2020,12(10): 1695.
[50]	樊红卫, 张旭辉, 曹现刚 ,等. 智慧矿山背景下我国煤矿机械故障诊断研究现状与展望[J]. 振动与冲击, 2020,39(24): 194-204.
	FAN H W , ZHANG X H , CAO X G ,et al. Research status and prospect of fault diagnosis of China’s coal mine machines under background of intelligent mine[J]. Journal of Vibration and Shock, 2020,39(24): 194-204.
[51]	WEN L , GAO L , LI X Y . A new deep transfer learning based on sparse auto-encoder for fault diagnosis[J]. IEEE Transactions on Systems,Man,and Cybernetics:Systems, 2019,49(1): 136-144.
[52]	LI K , XIONG M , LI F C ,et al. A novel fault diagnosis algorithm for rotating machinery based on a sparsity and neighborhood preserving deep extreme learning machine[J]. Neurocomputing, 2019,350: 261-270.
[53]	YU J B . A selective deep stacked denoising autoencoders ensemble with negative correlation learning for gearbox fault diagnosis[J]. Computers in Industry, 2019,108: 62-72.
[54]	ZHAO D F , LIU S L , GU D ,et al. Enhanced data-driven fault diagnosis for machines with small and unbalanced data based on variational auto-encoder[J]. Measurement Science and Technology, 2020,31(3): 035004.
[55]	YU J B , ZHOU X K . One-dimensional residual convolutional autoencoder based feature learning for gearbox fault diagnosis[J]. IEEE Transactions on Industrial Informatics, 2020,16(10): 6347-6358.
[56]	GAO W , QIAO S P , WAI R J ,et al. A newly designed diagnostic method for mechanical faults of high-voltage circuit breakers via SSAE and IELM[J]. IEEE Transactions on Instrumentation and Measurement, 2021,70: 1-13.
[57]	许卓斌, 郑海山, 潘竹虹 . 基于改进自编码器的文本分类算法[J]. 计算机科学, 2018,45(6): 208-210,240.
	XU Z B , ZHENG H S , PAN Z H . Improved autoencoder based classification algorithm for text[J]. Computer Science, 2018,45(6): 208-210,240.
[58]	JIANG M Y , LIANG Y C , FENG X Y ,et al. Text classification based on deep belief network and softmax regression[J]. Neural Computing and Applications, 2018,29(1): 61-70.
[59]	LI Q , LI P F , MAO K Z ,et al. Improving convolutional neural network for text classification by recursive data pruning[J]. Neurocomputing, 2020,414: 143-152.
[60]	冀俊忠, 庞皓明, 杨翠翠 ,等. 基于多隐层极限学习机的文本分类方法[J]. 北京工业大学学报, 2019,45(6): 534-545.
	JI J Z , PANG H M , YANG C C ,et al. Text classification method based on multi-layer extreme learning machine[J]. Journal of Beijing University of Technology, 2019,45(6): 534-545.
[61]	XU W D , TAN Y . Semisupervised text classification by variational autoencoder[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020,31(1): 295-308.
[62]	DONOHO D L . Compressed sensing[J]. IEEE Transactions on Information Theory, 2006,52(4): 1289-1306.
[63]	WANG M D , XIAO D , XIANG Y . Low-cost and confidentiality-preserving multi-image compressed acquisition and separate reconstruction for Internet of multimedia things[J]. IEEE Internet of Things Journal, 2021,8(3): 1662-1673.
[64]	RAVISHANKAR S , BRESLER Y . MR image reconstruction from highly undersampled k-space data by dictionary learning[J]. IEEE Transactions on Medical Imaging, 2011,30(5): 1028-1041.
[65]	TAO L , JIANG X , LIU X Z ,et al. Multiscale supervised kernel dictionary learning for SAR target recognition[J]. IEEE Transactions on Geoscience and Remote Sensing, 2020,58(9): 6281-6297.
[66]	QIN C , SCHLEMPER J , CABALLERO J ,et al. Convolutional recurrent neural networks for dynamic MR image reconstruction[J]. IEEE Transactions on Medical Imaging, 2019,38(1): 280-290.
[67]	张帅勇, 刘美琴, 姚超 ,等. 分级特征反馈融合的深度图像超分辨率重建[J]. 自动化学报, 2020,46: 1-12.
	ZHANG S Y , ZHANG M Q , YAO C ,et al. Hierarchical feature feedback network for depth super-resolution reconstruction[J]. Acta Automatica Sinica, 2020,46: 1-12.
[68]	TAN C C , ESWARAN C . Reconstruction and recognition of face and digit images using autoencoders[J]. Neural Computing and Applications, 2010,19(7): 1069-1079.
[69]	MEHTA J , MAJUMDAR A . RODEO:robust DE-aliasing autoencoder for real-time medical image reconstruction[J]. Pattern Recognition, 2017,63: 499-510.
[70]	ZHOU W Z , DU H Q , MEI W B ,et al. Efficient structurally-strengthened generative adversarial network for MRI reconstruction[J]. Neurocomputing, 2021,422: 51-61.
[71]	DABIRI S , LU C T , HEASLIP K ,et al. Semi-supervised deep learning approach for transportation mode identification using GPS trajectory data[J]. IEEE Transactions on Knowledge and Data Engineering, 2020,32(5): 1010-1023.
[72]	YUAN X , GU Y , WANG Y ,et al. A deep supervised learning framework for data-driven soft sensor modeling of industrial processes[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020,31(11): 4737-4746.
[73]	LIU Z , LI J G , SHEN Z Q ,et al. Learning efficient convolutional networks through network slimming[C]// 2017 IEEE International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2017: 2755-2763.
[74]	XIANG Q , WANG X D , SONG Y F ,et al. One-dimensional convolutional neural networks for high-resolution range profile recognition via adaptively feature recalibrating and automatically channel pruning[J]. International Journal of Intelligent Systems, 2021,36(1): 332-361.
[75]	王晓丹, 来杰, 李睿 ,等. 多层去噪极限学习机[J]. 吉林大学学报(工学版), 2020,50(3): 1031-1039.
	WANG X D , LAI J , LI R ,et al. Multilayer denoising extreme learning machine[J]. Journal of Jilin University (Engineering and Technology Edition), 2020,50(3): 1031-1039.
[76]	LI S , KAWALE J , FU Y . Deep collaborative filtering via marginalized denoising auto-encoder[C]// Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. New York:ACM Press, 2015: 811-820.
[77]	LAMATA L , ALVAREZ-RODRIGUEZ U , MARTíN-GUERRERO J D ,et al. Quantum autoencoders via quantum adders with genetic algorithms[J]. Quantum Science and Technology, 2018,4(1): 014007.
[78]	SUN Y N , XUE B , ZHANG M J ,et al. A particle swarm optimization-based flexible convolutional autoencoder for image classification[J]. IEEE Transactions on Neural Networks and Learning Systems, 2019,30(8): 2295-2309.
[79]	GLOROT X , BENGIO Y . Understanding the difficulty of training deep feedforward neural networks[C]// Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics. New York:ACM Press, 2010: 249-256.
[80]	HE K M , ZHANG X Y , REN S Q ,et al. Delving deep into rectifiers:surpassing human-level performance on ImageNet classification[C]// 2015 IEEE International Conference on Computer Vision (ICCV). Piscataway:IEEE Press, 2015: 1026-1034.

算法	目的	实现方式	特点
AE	特征提取特征降维	由编码器与解码器组成，前者完成样本的抽象特征表示，后者完成输入样本的重构，通过梯度下降算法完成迭代微调	确定型无监督学习模型，能有效提取高级抽象特征，但所提取特征的稀疏性、稳健性不足
RBM	特征提取特征降维	由可见层与隐含层组成，旨在最大化可见变量与隐含变量联合概率分布的似然函数，通过对比散度算法完成迭代微调	概率型无监督学习模型，能有效提取高级抽象特征，但易产生过拟合现象
GAN	数据生成	由生成器与判别器组成，旨在通过生成器与判别器的二元博弈提升生成样本质量，网络参数的优化由梯度下降算法完成	无监督生成模型，能生成高质量样本，但易发生模式崩溃问题
SOM	聚类分析特征提取特征降维	由输入层与竞争层组成，旨在通过竞争学习策略逐步优化网络，近邻关系函数维持输入样本的拓扑结构，进而完成样本的低维映射	浅层无监督学习模型，具有独特的竞争学习机制，能有效生成样本的低维映射，但不适用于高维特征的提取

自编码器及其应用综述

Review on autoencoder and its application

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 80

相关文章 15

Metrics

推荐阅读 0

[1]	陈东昱, 陈华, 范丽敏, 付一方, 王舰. 基于深度学习的随机性检验策略研究[J]. 通信学报, 2023, 44(6): 23-33.
[2]	李荣鹏, 汪丙炎, 张宏纲, 赵志峰. 知识增强的语义通信接收端设计[J]. 通信学报, 2023, 44(6): 70-76.
[3]	马帅, 裴科, 祁华艳, 李航, 曹雯, 王洪梅, 熊海良, 李世银. 基于生成模型的地磁室内高精度定位算法研究[J]. 通信学报, 2023, 44(6): 211-222.
[4]	王一丰, 郭渊博, 陈庆礼, 方晨, 林韧昊, 周永良, 马佳利. 基于对比增量学习的细粒度恶意流量分类方法[J]. 通信学报, 2023, 44(3): 1-11.
[5]	江沸菠, 彭于波, 董莉. 面向6G的深度图像语义通信模型[J]. 通信学报, 2023, 44(3): 198-208.
[6]	霍纬纲, 梁锐, 李永华. 基于随机Transformer的多维时间序列异常检测模型[J]. 通信学报, 2023, 44(2): 94-103.
[7]	王延文, 雷为民, 张伟, 孟欢, 陈新怡, 叶文慧, 景庆阳. 基于生成模型的视频图像重建方法综述[J]. 通信学报, 2022, 43(9): 194-208.
[8]	杨洁, 董标, 付雪, 王禹, 桂冠. 基于轻量化分布式学习的自动调制分类方法[J]. 通信学报, 2022, 43(7): 134-142.
[9]	张文林, 刘雪鹏, 牛铜, 陈琦, 屈丹. 基于正样本对比与掩蔽重建的自监督语音表示学习[J]. 通信学报, 2022, 43(7): 163-171.
[10]	杨秀璋, 彭国军, 李子川, 吕杨琦, 刘思德, 李晨光. 基于Bert和BiLSTM-CRF的APT攻击实体识别及对齐研究[J]. 通信学报, 2022, 43(6): 58-70.
[11]	兰巨龙, 朱棣, 李丹. 面向多模态网络业务切片的虚拟网络功能资源容量智能预测方法[J]. 通信学报, 2022, 43(6): 143-155.
[12]	王晓丹, 李京泰, 宋亚飞. DDAC：面向卷积神经网络图像隐写分析模型的特征提取方法[J]. 通信学报, 2022, 43(5): 68-81.
[13]	廖勇, 王世义. 高速移动环境下基于RM-Net的大规模MIMO CSI反馈算法[J]. 通信学报, 2022, 43(5): 166-176.
[14]	廖育荣, 王海宁, 林存宝, 李阳, 方宇强, 倪淑燕. 基于深度学习的光学遥感图像目标检测研究进展[J]. 通信学报, 2022, 43(5): 190-203.
[15]	赵增华, 童跃凡, 崔佳洋. 基于域自适应的Wi-Fi指纹设备无关室内定位模型[J]. 通信学报, 2022, 43(4): 143-153.