Computer Science ›› 2018, Vol. 45 ›› Issue (1): 280-284.doi: 10.11896/j.issn.1002-137X.2018.01.049

Previous Articles     Next Articles

Transfer Prediction Learning Based on Hybrid of SDA and SVR

REN Jun, HU Xiao-feng and LI Ning   

  • Online:2018-01-15 Published:2018-11-13

Abstract: To improve the prediction accuracy of small sample in the era of big data,this paper introduced a novel hybrid model based on stacked denoising auto-encoder(SDA) and support vector regression (SVR).The hybrid model is pretrained by using a large number of source domain data,and then it is fine-tuned by a small amount of target domain data.The method takes the advantage of SDA,extracting common features autonomously on related but different target domain data.By transferring these prior knowledge,the hybrid model can provide a relatively accurate prediction result on high-dimensional and noisy small sample.Experimental results on extensive datasets demonstrate the effectiveness of the proposed model.

Key words: Transfer learning,Feature extraction,Stacked denoising auto-encoder

[1] TAO J W,CHUNG F L,WANG S T.A kernel learning framework for domain adaptation learning[J].Science China Information Sciences,2012,5(9):1983-2007.
[2] PAN J L,YANG Q.A survey on transfer learning[J].IEEETrans.on knowledge and Data Engineering,2010,2(10):1345-1359.
[3] PANS J L,KWOK J T,YANG Q.Transferring learning viadimensionality reduction[C]∥Proc.of the 23st National Con-ference on Artificial Intelligence.Menlo Park:AAAI Press,2008:677-682.
[4] WEI F M,ZHANG J P,CHU Y,et al.FSFP:Transfer learning from long texts to the short[J].Applied Mathematics & Information Sciences,2014,8(4):2033-2044.
[5] OQUAB M M,BOTTOU L,LAPTEV I,et al.Learning andTransferring Mid-level Image Representations Using Convolutional Neural Networks [C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).USA:IEEE Computer Society,2014:1717-l724.
[6] AREL I,ROSE D C,KARNOWSKI T P.Deep Machine Lear-ning-A new Frontier in Artificial intelligence research[J].IEEE Computational Intelligence Magazine,2010,5(4):13-18.
[7] LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(5):436-444.
[8] YU K,JIA L,CHEN Y Q,et al.Deep Learning.Yesterday,Today,and Tomorrow[J].Journal of Computer Research and Dve-lopment,2013,0(9):1799-1804.(in Chinese) 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,2013,0(9):1799-1804.
[9] BENGIO Y .Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-127.
[10] HINTON G,SALAKHUTDINOV R R.Reducing the dimen-sionality of data with neural networks[J].Science,2006,313(5786):504-507.
[11] ZHANG L,LIU Z,ZHANG J Q,et al.Reduction method of weapon system-of-systems assessment index system based on autoencoder[J].Journal of Central South University(Science and Technology),2013,4(10):4130-4137.(in Chinese) 张乐,刘忠,张建强,等.基于自编码神经网络的装备体系评估指标约简方法[J].中南大学学报(自然科学版),2013,4(10):4130-4137.
[12] HU Z,FU K,ZHANG C S.Audio Classical Composer Identification by Deep Neural Network[J].Journal of Computer Research and Development,2014,1(9):1945-1954.(in Chinese) 胡振,傅昆,张长水.基于深度学习的作曲家分类问题[J].计算机研究与发展,2014,1(9):1945-1954.
[13] SONG C F,LIU F,HUANG Y Z,et al.Auto-encoder based Data clustering[C]∥Proceeding,Part I,of the 18th Iberoamerican Congress on Progress in Pattern Recognition,Image Analysis,Computer Vision,and Applications.Springer-verlag:New York,2013:117-124.
[14] VINCENT P,LAROCHELLE H,BENGIO Y ,et al.Extractingand composing robust features with denoising autoeneoders[C]∥ Proceedings of the 25th International Conference on Machine Learning.New York,NY,USA:ACM,2008:1096-1103.
[15] BENGIO Y,LAMBLIN P,LAROCHELLE H,et al.Greedylayerwise training of deep networks[J].Advances in Neural Information Processing Systems,2007,19:153-160.
[16] GAN M T,HANMANDLU M,TAN A H.From a Gaussianmixture model to additive fuzzy systems[J].IEEE Transactions on Fuzzy Systems,2005,3(3):303-316.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!