Extract Features Using Stacked Denoised Autoencoder

In this paper, a novel neural network, DenoisedAutoEncoder (DAE) is introduced first. This neural network is applied for extracting the features. In this paper, we proved that stacked DAE can extract good features for classification task. We apply the stacked DAE to extract features of leave pictures, and then we classify leaves using those features with SVM, the result suggests that this method surpass pure SVM.

[1]  De-Shuang Huang,et al.  Locally linear discriminant embedding: An efficient method for face recognition , 2008, Pattern Recognit..

[2]  Yoshua. Bengio,et al.  Learning Deep Architectures for AI , 2007, Found. Trends Mach. Learn..

[3]  De-Shuang Huang,et al.  A Neural Root Finder of Polynomials Based on Root Moments , 2004, Neural Computation.

[4]  Geoffrey E. Hinton Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[5]  Xiaofeng Wang,et al.  An efficient local Chan-Vese model for image segmentation , 2010, Pattern Recognit..

[6]  De-Shuang Huang,et al.  A Constructive Hybrid Structure Optimization Methodology for Radial Basis Probabilistic Neural Networks , 2008, IEEE Transactions on Neural Networks.

[7]  Pascal Vincent,et al.  Stacked Denoising Autoencoders: Learning Useful Representations in a Deep Network with a Local Denoising Criterion , 2010, J. Mach. Learn. Res..

[8]  D.-S. Huang,et al.  Radial Basis Probabilistic Neural Networks: Model and Application , 1999, Int. J. Pattern Recognit. Artif. Intell..

[9]  H. Bourlard,et al.  Auto-association by multilayer perceptrons and singular value decomposition , 1988, Biological Cybernetics.

[10]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[12]  Yoshua Bengio,et al.  Extracting and composing robust features with denoising autoencoders , 2008, ICML '08.