Computer Science ›› 2015, Vol. 42 ›› Issue (11): 288-292.doi: 10.11896/j.issn.1002-137X.2015.11.059

Previous Articles     Next Articles

Feature Extraction Algorithm Based on Evolutionary Deep Learning

CHEN Zhen, XIA Jing-bo, BAI Jun and XU Min   

  • Online:2018-11-14 Published:2018-11-14

Abstract: The contradiction of comprehensive information and dimension curse is the preliminary problem of network situation awareness in the times of big data.Feature extraction is a mainstream method to dimensionality reduction,but performs not well when solving high-dimension and nonlinear data.Deep learning is a multi-layer and nonlinear algorithm which can realize the approximation of complicated function,however,it is sensitive to parameters related to hidden layer.Based on above analysis,a feature extraction algorithm based on evolutionary deep learning was proposed.The algorithm combines evolutionary algorithm(EA) and deep learning,takes advantage of the characteristics of GA and ES,and optimizes the learning structure and relevant parameters.Theoretical analysis and simulation results both prove the effectiveness of this algorithm.

Key words: Network situation awareness,Feature extraction,Evolution algorithm,Deep learning,RBM

[1] 孙志军,薛磊,许阳明.基于深度学习的边际Fisher分析特征提取算法[J].电子与信息学报,2013,35(4):805-811 Sun Zhi-jun,Xue Lei,Xu Yang-ming.Marginal Fisher Feature Extraction Algorithm Based on Deep Learning[J].Journal of Electronics&Information Technology,2013,35(4):805-811
[2] Bengio Y,Delalleau O.On the expressive power of deep architecture [M]∥Algorithmic Learning Theory.Springer,2011:18-36
[3] Bengio Y.Deep Learning of representations for unsupervisedand transfer learning[C]∥JMLR.Washington,USA,2012:17-36
[4] 孙志军,薛磊,许阳明,等.深度学习研究综述[J].计算机应用研究,2012,29(8):2806-2810 Sun Zhi-jun,Xue Lei,Xu Yang-ming,et al.Overview of deep learning[J].Applicatin Research of Computers,2012,9(8):2806-2810
[5] Hinton G,Salakhutdinov R.Reducing the dimensionality of data with neural networks [J].Science,2006,3(5786):504-507
[6] 余凯,贾磊,陈雨强,等.深度学习的昨天、今天和明天[J].计算机研究与发展,2013,50(9):1799-1804 Yu Kai,Jia Lei,Chen Yu-qiang,et al.Deep learning:Yesterday,Today,and Tomorrow[J].Journal of Computer Research and Development,2013,0(9):1799-1804
[7] 刘建伟,刘媛,罗雄麟.波尔兹曼机研究进展[J].计算机研究与发展,2014,51(1):1-16 Liu Jian-wei,Liu Yuan,Luo Xiong-lin.Research and Development of Boltzmann Machine[J].Journal of Computer Research and Development,2014,1(1):1-16
[8] 徐敏,夏靖波,申健,等.基于LEAST的高速网络大流检测算法[J].空军工程大学学报,2015,8:25-30 Xu min,Xia Jing-bo,Shen Jian,et al.Based on LESET High-Speed Network Traffic Measurement Method[J].Journal of Air Force Engineering University,2015,8:25-30
[9] Hinton,Salakhudinov R.Training a deep auto-encoder or a clas-sifier on MINIST digits. For Science Paper.html
[10] Kantardzic M.Data Mining:Conception,Model,and Algorithm(Edition 2)[M].Beijing:Tsinghua University press,2013
[11] Bengio Y,Lamblin P,Popovici D,et al.Greedy layer-wise trai-ning of deep networks [C]∥Proc of the 12th Annual Conference on Neural Information Processing System.2006:153-160
[12] Hinton G,Osindero S,Teh Y.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,8(7):1527-1554
[13] 方敏,王宝树.基于进化策略的多传感器雷达辐射源目标识别方法[J].控制理论与应用,2004,21(2):165-168 Fang Min,Wang Bao-shu.Multi-sensor radar radiation source target recognition based on evolution strategy method[J].Control Theory and Application,2004,1(2):165-168
[14] 李鸿儒,王晓楠,高仝.基于免疫进化策略的神经网络优化方法[J].东北大学学报(自然科学版),2008,29(6):794-797 Li Hong-ru,Wang Xiao-nan,Gao Tong.Optimization Algorithm Based on Immune Evolutionary Strategy of Neural Network[J].Journal of Northeast University(Natural Science),2008,9(6):794-797
[15] Bengio Y.Learning Deep Architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-127
[16] Deep Learning和Knowledge Graph引爆大数据革命.
[17] Boltzmann神经网络模型与学习算法.
[18] 浅谈Deep Learning的基本思想和方法.
[19] Deep Learning. research/deep/

No related articles found!
Full text



No Suggested Reading articles found!