计算机科学 ›› 2018, Vol. 45 ›› Issue (6A): 11-15.
付文博1,孙涛2,梁藉1,闫宝伟1,范福新1
FU Wen-bo1,SUN Tao2,LIANG Ji1,YAN Bao-wei1,FAN Fu-xin1
摘要: 深度学习作为机器学习领域中重要的技术手段,有着广阔的应用前景。文中简述了深度学习的发展历程,介绍了卷积神经网络、受限玻尔兹曼机、自动编码器及其衍生的系列方法模型,以及Caffe,TensorFlow,Torch等6种主流深度框架;论述了深度学习在图像、语音、视频、文本、数据分析方面的应用情况,分析了深度学习现阶段存在的问题以及未来的发展趋势,为初学者提供了较全面的方法指导与文献索引支持。
中图分类号:
[1]MCCULLOCH W S,PITTS W H.A logical calculus of ideas imminent in nervous activity.Biol Math Biophys,1943,5:115-133 [2]ROSENBLATT F.Two Theorems of Statistical Separability in the Perceptron.https://www.researchgate.net/publication/243614378_Two_Theorems_of_Statistical_Separability_in_the_Perceptron. [3]MINSKY M L,PAPERT S.Perceptrons:an introduction to com- putational geometry[M]∥Perceptrons:An Introduction to Computational Geometry.The MIT Press,1969:3356-62. [4]RUMELHART D E,HINTON G E,WILLIAMS R J.Learning internal representation by back-propagation of errors.Nature,1986,323(323):533-536. [5]HINTON G E,OSINDERO S,TEH Y W.A Fast Learning Algorithm for Deep Belief Nets.Neural Computation,2006,18(7):1527. [6]BROWNE M,GHIDARY S S.Convolutional Neural Networks for Image Processing:An Application in Robot Vision[C]∥Conference on Ai:Advances in Artificial Intelligence.DBLP,2003:641-652. [7]HAYKIN S,KOSKO B.Gradient Based Learning Applied to Document Recognition.New Jersey:Wiley-IEEE Press,2009:306-351. [8]LECUN Y,BENGIO Y,HINTON G.Deep learning.Nature,2015,521(7553):436-444. [9]PALIY I.Face detection using Haar-like features cascade and convolutional neural network[C]∥Proceedings of International Conference on Modern Problems of Radio Engineering,Telecommunications and Computer Science.IEEE,2008:375-377. [10]HUBEL D H,WIESEL T N.Receptive fields,binocular interaction and functional architecture in the cat’s visual cortex.Journal of Physiology,1962,160(1):106-154. [11]KRUTHIVENTI S S S,AYUSH K,BABU R V.DeepFix:A Fully Convolutional Neural Network for Predicting Human Eye Fixations.IEEE Transactions on Image Processing,2015,26(9):4446-4456. [12]郭昕,陈琳,沉敏.分层自适应深度卷积神经网络及其在轴承故障诊断中的应用.测量,2016,93:490-502. [13]SMOLENSKY P.Information processing in dynamical systems: foundations of harmony theory[M]∥Parallel distributed processing:explorations in the microstructure of cognition.MIT Press,1986:194-281. [14]SALAKHUTDINOV R,LAROCHELLE H.Efficient Learning of Deep Boltzmann Machines.https://www.researchgate.net/publication/220320264_Efficient_Learning_of_Deep_Boltzmann_Machines. [15]罗恒.基于协同过滤视角的受限玻尔兹曼机研究.上海:上海交通大学,2011. [16]LAROCHELLE H,MANDEL M,PASCANU R,et al.Learning algorithms for the classification restricted Boltzmann machine.Journal of Machine Learning Research,2012,13(1):643-669. [17]SCHLKOPF B,PLATT J,HOFMANN T.Greedy Layer- Wise Training of Deep Networks[C]∥International Conference on Neural Information Processing Systems.MIT Press,2006:153-160. [18]LEE H,GROSSE R,RANGANATH R,et al.Unsupervised learning of hierarchical representations with convolutional deep belief networks.Communications of the Acm,2011,54(10):95-103. [19]HALKIAS X,PARIS S ,GLOTIN H.Sparse Penalty in Deep Belief Networks:Using the Mixed Norm Constraint .(2013-01-16).http://arxiv.org/pdf/1301.3533vl.pdf. [20]GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al. Generative Adversarial Networks.Advances in Neural Information Processing Systems,2014,3:2672-2680. [21]HINTON G E,SALAKHUTDINOV R R.Reducing the Dimensionality of Data with Neural Networks.Science,2006,313(5786):504-507. [22]BENGIO Y,LAMBLIN P,POPOVICI D,et al.Greedy layer-wise training of deep networks[C]∥International Conference on Neural Information Processing Systems.MIT Press,2006:153-160. [23]RANZATO M,BOUREAU Y L,LECUN Y.Sparse feature learning for deep belief networks[C]∥Advances in Neural Information Processing Systems.2007:1185-1192. [24]VINCENT P,LAROCHELLE H,BENGIO Y,et al.Extracting and composing robust features with denoising autoencoders[C]∥27th International Conference on Machine Learning.ACM.2008:1096-1103. [25]VINCENT P,LAROCHELLE H,LAJOIE I,et al.Stacked Denoising Autoencoders:Learning Useful Representations in a Deep Network with a Local Denoising Criterion..Journal of Machine Learning Research,2010,11(12):3371-3408. [26]MASCI J,MEIER U,DAN C,et al.Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction[C]∥International Conference on Artificial Neural Networks.2011:52-59. [27]JIANG X,ZHANG Y,ZHANG W,et al.A novel sparse auto-encoder for deep unsupervised learning[C]∥Sixth International Conference on Advanced Computational Intelligence.IEEE,2014:256-261. [28]JIA Y,SHELHAMER E,DONAHUE J,et al.Caffe:Convolutional Architecture for Fast Feature Embedding[C]∥Acm International Conference on Multimedia.ACM,2014:675-678. [29]ABADI M.TensorFlow:learning functions at scale.AcmSigplan Notices,2016,51(9):1. [30]SEIDE F.Keynote:The computer science behind the Microsoft Cognitive Toolkit:An open source large-scale deep learning toolkit for Windows and Linux[C]∥Ieee/acm International Symposium on Code Generation and Optimization.IEEE,2017. [31]YANG H,FRITZSCHE M,BARTZ C,et al.BMXNet:An Open- Source Binary Neural Network Implementation Based on MXNet[C]∥ACM.2017:1209-1212. [32]SANKARAN A,ARALIKATTE R,MANI S,et al.DARVIZ:deep abstract representation,visualization,and verification of deep learning models[C]∥Ieee/acm,International Conference on Software Engineering:New Ideas and Emerging Technologies Results Track.IEEE,2017:47-50. [33]BOUFENAR C,BATOUCHE M.Investigation on deep learning for off-line handwritten Arabic Character Recognition using Theano research platform[C]∥Intelligent Systems and Computer Vision.IEEE,2017. [34]魏英姿,谭龙田,欧阳海飞,等.玉米籽粒完整性识别的深度学习方法.沈阳理工大学学报,2016,35(4):1-6. [35]李楠.基于深度学习框架Caffe的路面裂缝识别研究.工程技术研究,2017(3):20,28. [36]杜敬.基于深度学习的无人机遥感影像水体识别.江西科学,2017,35(1):158-161. [37]寇广,汤光明,王硕,等.深度学习在僵尸云检测中的应用研究.通信学报,2016,37(11):114-128. [38]刘大伟,韩玲,韩晓勇.基于深度学习的高分辨率遥感影像分类研究.光学学报,2016,36(4):298-306. [39]樊恒,徐俊,邓勇,等.基于深度学习的人体行为识别.武汉大学学报(信息科学版),2016,41(4):492-497. [40]李婷.基于深度学习的盲文识别方法.计算机与现代化,2015,238(6):37-40. [41]阚希,张永宏,曹庭,等.利用多光谱卫星遥感和深度学习方法进行青藏高原积雪判识.测绘学报,2016,45(10):1210-1221. [42]HINTON G,DENG L,YU D,et al.Deep Neural Networks for Acoustic Modeling in Speech Recognition:The Shared Views of Four Research Groups.IEEE Signal Processing Magazine,2012,29(6):82-97. [43]王山海,景新幸,杨海燕.基于深度学习神经网络的孤立词语音识别的研究.计算机应用研究,2015,32(8):2289-2291. [44]王强,曾向阳.深度学习方法及其在水下目标识别中的应用[C]∥中国声学学会水声学分会学术会议.2015:139-141. [45]张剑.连续语音识别中的循环神经网络语言模型技术研究.郑州:解放军信息工程大学,2014. [46]LU X G,TSAO Y,MATSUDA S,et al.Speech enhancement based on deep denoising autoencoder∥The 14th Annual Conference of the International Speech Communication Association.Lyon:ISCA Archive,2013:436-440 [47]GREFF K,SRIVASTAVA R K,KOUTN K J,et al.LSTM:A Search Space Odyssey.IEEE Transactions on Neural Networks & Learning Systems,2015,28(10):2222-2232. [48]杨红红,曲仕茹.基于稀疏约束深度学习的交通目标跟踪.中国公路学报,2016,29(6):253-261. [49]司朋举,胡伟.深度学习在仿生眼监控系统中的应用.测控技术,2016,35(12):139-143. [50]王慧燕,杨宇涛,张政,等.深度学习辅助的多行人跟踪算法.中国图象图形学报,2017,22(3):349-357. [51]文孟飞,胡超,刘伟荣.一种基于深度学习的异构多模态目标识别方法.中南大学学报(自然科学版),2016,47(5):1580-1587. [52]张立民,刘凯.基于深度玻尔兹曼机的文本特征提取研究.微电子学与计算机,2015,32(2):142-147. [53]周盈盈,范磊.基于改进词向量模型的深度学习文本主题分类.计算机科学与应用,2016,6(11):629-637. [54]李阳辉,谢明,易阳.基于深度学习的社交网络平台细粒度情感分析.计算机应用研究,2017,34(3):743-747. [55]雷亚国,贾峰,周昕,等.基于深度学习理论的机械装备大数据健康监测方法.机械工程学报,2015,51(21):49-56. [56]潘儒扬,李乡儒.基于深度学习技术的恒星大气物理参数自动估计.天文学报,2016,57(4):379-388. [57]谭娟,王胜春.基于深度学习的交通拥堵预测模型研究.计算机应用研究,2015,32(10):2951-2954. [58]潘志刚,刘三明,李莹,等.基于深度学习网络的风电场功率短期预测研究.科技与创新,2015,43(19):4-6. [59]夏春江,王培良,张媛.基于深度学习的木材含水率预测.杭州电子科技大学学报,2015,35(1):31-35. [60]姚俊杨,许继平,王小艺,等.基于深度学习的湖库藻类水华预测研究.计算机与应用化学,2015,32(10):1265-1268. |
[1] | 饶志双, 贾真, 张凡, 李天瑞. 基于Key-Value关联记忆网络的知识图谱问答方法 Key-Value Relational Memory Networks for Question Answering over Knowledge Graph 计算机科学, 2022, 49(9): 202-207. https://doi.org/10.11896/jsjkx.220300277 |
[2] | 宁晗阳, 马苗, 杨波, 刘士昌. 密码学智能化研究进展与分析 Research Progress and Analysis on Intelligent Cryptology 计算机科学, 2022, 49(9): 288-296. https://doi.org/10.11896/jsjkx.220300053 |
[3] | 汤凌韬, 王迪, 张鲁飞, 刘盛云. 基于安全多方计算和差分隐私的联邦学习方案 Federated Learning Scheme Based on Secure Multi-party Computation and Differential Privacy 计算机科学, 2022, 49(9): 297-305. https://doi.org/10.11896/jsjkx.210800108 |
[4] | 周芳泉, 成卫青. 基于全局增强图神经网络的序列推荐 Sequence Recommendation Based on Global Enhanced Graph Neural Network 计算机科学, 2022, 49(9): 55-63. https://doi.org/10.11896/jsjkx.210700085 |
[5] | 周乐员, 张剑华, 袁甜甜, 陈胜勇. 多层注意力机制融合的序列到序列中国连续手语识别和翻译 Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion 计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026 |
[6] | 徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204 |
[7] | 李宗民, 张玉鹏, 刘玉杰, 李华. 基于可变形图卷积的点云表征学习 Deformable Graph Convolutional Networks Based Point Cloud Representation Learning 计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023 |
[8] | 王剑, 彭雨琦, 赵宇斐, 杨健. 基于深度学习的社交网络舆情信息抽取方法综述 Survey of Social Network Public Opinion Information Extraction Based on Deep Learning 计算机科学, 2022, 49(8): 279-293. https://doi.org/10.11896/jsjkx.220300099 |
[9] | 郝志荣, 陈龙, 黄嘉成. 面向文本分类的类别区分式通用对抗攻击方法 Class Discriminative Universal Adversarial Attack for Text Classification 计算机科学, 2022, 49(8): 323-329. https://doi.org/10.11896/jsjkx.220200077 |
[10] | 姜梦函, 李邵梅, 郑洪浩, 张建朋. 基于改进位置编码的谣言检测模型 Rumor Detection Model Based on Improved Position Embedding 计算机科学, 2022, 49(8): 330-335. https://doi.org/10.11896/jsjkx.210600046 |
[11] | 王润安, 邹兆年. 基于物理操作级模型的查询执行时间预测方法 Query Performance Prediction Based on Physical Operation-level Models 计算机科学, 2022, 49(8): 49-55. https://doi.org/10.11896/jsjkx.210700074 |
[12] | 陈泳全, 姜瑛. 基于卷积神经网络的APP用户行为分析方法 Analysis Method of APP User Behavior Based on Convolutional Neural Network 计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121 |
[13] | 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥. 基于注意力机制的医学影像深度哈希检索算法 Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism 计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153 |
[14] | 孙奇, 吉根林, 张杰. 基于非局部注意力生成对抗网络的视频异常事件检测方法 Non-local Attention Based Generative Adversarial Network for Video Abnormal Event Detection 计算机科学, 2022, 49(8): 172-177. https://doi.org/10.11896/jsjkx.210600061 |
[15] | 檀莹莹, 王俊丽, 张超波. 基于图卷积神经网络的文本分类方法研究综述 Review of Text Classification Methods Based on Graph Convolutional Network 计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064 |
|